@inproceedings{okada-etal-2026-lenslapse,
title = "{L}ens{L}apse: In-Browser Logit Lens for Interactive Exploration of Language Model Training Dynamics",
author = "Okada, Tatsuki and
Sakai, Yusuke and
Watanabe, Taro",
editor = "Zhang, Ningyu and
Wijaya, Derry",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics: System Demonstrations",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-demo.9/",
pages = "66--73",
ISBN = "979-8-89176-441-5",
abstract = "The logit lens is a standard mechanistic interpretability tool for inspecting a Transformer{'}s predictions across layers. However, existing logit lens tools typically focus on individual checkpoints rather than interactive exploration of a model{'}s *training history*.\par In this study, we introduce **LensLapse**, an open-source web application for interactive exploration of a model{'}s training history through token-level interpretability. Users can scrub a slider across public checkpoints from five model families and three multilingual checkpoint suites and observe how per-layer, per-position logit lens predictions evolve from frequency bias to factual knowledge.\par For browser-compatible models, arbitrary user prompts are probed *live in the browser* via local inference over per-checkpoint model pairs. No server, no API key, no hosting cost, and prompts never leave the user{'}s device.\par Moreover, **LensLapse** supports local models. A single `pip install{`} enables users to launch the application and explore their own models and training checkpoints without any additional web setup.\par LensLapse is MIT-licensed and permanently hosted at iamtatsuki05.github.io/lenslapse.\par - GitHub: https://github.com/iamtatsuki05/lenslapse - PyPI: https://pypi.org/project/lenslapse/ - docs: https://iamtatsuki05.github.io/lenslapse/docs/ - YouTube: https://youtu.be/OBnvG9Ru3j8"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="okada-etal-2026-lenslapse">
<titleInfo>
<title>LensLapse: In-Browser Logit Lens for Interactive Exploration of Language Model Training Dynamics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tatsuki</namePart>
<namePart type="family">Okada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Sakai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ningyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derry</namePart>
<namePart type="family">Wijaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-441-5</identifier>
</relatedItem>
<abstract>The logit lens is a standard mechanistic interpretability tool for inspecting a Transformer’s predictions across layers. However, existing logit lens tools typically focus on individual checkpoints rather than interactive exploration of a model’s *training history*.\par In this study, we introduce **LensLapse**, an open-source web application for interactive exploration of a model’s training history through token-level interpretability. Users can scrub a slider across public checkpoints from five model families and three multilingual checkpoint suites and observe how per-layer, per-position logit lens predictions evolve from frequency bias to factual knowledge.\par For browser-compatible models, arbitrary user prompts are probed *live in the browser* via local inference over per-checkpoint model pairs. No server, no API key, no hosting cost, and prompts never leave the user’s device.\par Moreover, **LensLapse** supports local models. A single ‘pip install‘ enables users to launch the application and explore their own models and training checkpoints without any additional web setup.\par LensLapse is MIT-licensed and permanently hosted at iamtatsuki05.github.io/lenslapse.\par - GitHub: https://github.com/iamtatsuki05/lenslapse - PyPI: https://pypi.org/project/lenslapse/ - docs: https://iamtatsuki05.github.io/lenslapse/docs/ - YouTube: https://youtu.be/OBnvG9Ru3j8</abstract>
<identifier type="citekey">okada-etal-2026-lenslapse</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-demo.9/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>66</start>
<end>73</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings %T LensLapse: In-Browser Logit Lens for Interactive Exploration of Language Model Training Dynamics %A Okada, Tatsuki %A Sakai, Yusuke %A Watanabe, Taro %Y Zhang, Ningyu %Y Wijaya, Derry %S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations %D 2026 %8 November %I Association for Computational Linguistics %C Hengqin, China %@ 979-8-89176-441-5 %F okada-etal-2026-lenslapse %X The logit lens is a standard mechanistic interpretability tool for inspecting a Transformer’s predictions across layers. However, existing logit lens tools typically focus on individual checkpoints rather than interactive exploration of a model’s *training history*.\par In this study, we introduce **LensLapse**, an open-source web application for interactive exploration of a model’s training history through token-level interpretability. Users can scrub a slider across public checkpoints from five model families and three multilingual checkpoint suites and observe how per-layer, per-position logit lens predictions evolve from frequency bias to factual knowledge.\par For browser-compatible models, arbitrary user prompts are probed *live in the browser* via local inference over per-checkpoint model pairs. No server, no API key, no hosting cost, and prompts never leave the user’s device.\par Moreover, **LensLapse** supports local models. A single ‘pip install‘ enables users to launch the application and explore their own models and training checkpoints without any additional web setup.\par LensLapse is MIT-licensed and permanently hosted at iamtatsuki05.github.io/lenslapse.\par - GitHub: https://github.com/iamtatsuki05/lenslapse - PyPI: https://pypi.org/project/lenslapse/ - docs: https://iamtatsuki05.github.io/lenslapse/docs/ - YouTube: https://youtu.be/OBnvG9Ru3j8 %U https://aclanthology.org/2026.aacl-demo.9/ %P 66-73
Markdown (Informal)
[LensLapse: In-Browser Logit Lens for Interactive Exploration of Language Model Training Dynamics](https://aclanthology.org/2026.aacl-demo.9/) (Okada et al., AACL-IJCNLP 2026)