Mechanistic Interpretability

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

12 new papers

A weekly snapshot of new work published in Mechanistic Interpretability.

Period ending 2026-09-14

10 new papers

A weekly snapshot of new work published in Mechanistic Interpretability.

Period ending 2026-09-07

13 new papers

A weekly snapshot of new work published in Mechanistic Interpretability.

Inside this field

Focused directions

Focused topic

Model Interpretability

Within Mechanistic Interpretability

269 papersExplore

Focused topic

Mechanistic Interpretability

Within Mechanistic Interpretability

158 papersExplore

Focused topic

Interpretable Models

Within Mechanistic Interpretability

38 papersExplore

434 papers

Latest in Mechanistic Interpretability

Browse all topics →

The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology
Jul 1, 2026Andrzej Szablewski, Gabriel Konar-Steenberg, Raffaello Fornasiere +2Model Interpretability Model Activations
Domain Knowledge Based Temporal-Spatial Graph Convolution Network for ECG Recognition
Jul 1, 2026Wenting Ma, Zhipeng Zhang, Xiaohang Yuan +6Pediatric-Adult Electrocardiogram Alignment Temporal Graph Neural Networks
Caption Bottleneck Models
Jul 1, 2026Seref Baris Cagliyan, Umut Ozdemir, Merve Tapli +1Concept Bottleneck Models Model Interpretability
Multilayer Q-Matrix-Embedded Neural Network for Cognitive Diagnosis (M-QCDNet): Structure-Aware Deep Learning Architecture for Psychometric Interpretability
Jul 1, 2026Yiyao YangCognitive Diagnosis Model Interpretability
Representation as a Bottleneck for Mechanistic Interpretability: The Manifestation Unit Protocol
Jun 30, 2026Hussein Chouman, Wataru Sasaki, Tomokazu Matsui +2Mechanistic Interpretability Model Interpretability
Surrogate Fidelity: When Can Open LLMs Explain Closed Ones?
Jun 30, 2026Philippe Chlenski, Zachariah Carmichael, Ayush Warikoo +5Mechanistic Interpretability Closure
Resolving superposition in AI for interpretability and cross-modal alignment in patient-neuronal images
Jun 30, 2026Jisung Park, Seohyeon Kang, Daeun Yoo +8Neuroimaging Models Implicit Neural Representations
Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again
Jun 30, 2026Zakk Heile, Hayden McTavish, Margo Seltzer +1Decision Trees Interpretable Models
Partition-Guided Distance Saliency: Bridging Decision and Objective Spaces in Many-Objective Optimization
Jun 29, 2026Cláudio Lúcio do Val Lopes, Flávio Vinícius Cruzeiro Martins, Elizabeth Fialho WannerMulti-Objective Optimization Saliency
Improved Predictive Performance and Interpretability for Mesomorphic Neural Networks Using Local Fidelity Regularization
Jun 29, 2026Hugo L. Hammer, Vajira Thambawita, Kristoffer Herland Hellton +1Model Interpretability Regularization Techniques
t-STEP: An interpretable model for Total Electron Content predictions and irregularities estimations
Jun 28, 2026Stephen Tete, Carl Shneider, Maxime Cordy +3Geomagnetic Storms Interpretable Models
Symbolic Mechanistic Data Attribution: Tracing Training Influence to Learned Behavioral Policies
Jun 28, 2026Reza Habibi, Darian Lee, Magy Seif El-NasrTraining Data Attribution Mechanistic Interpretability
Mechanistic Personality Analysis of LLMs Steering Personality via Latent Feature Interventions
Jun 27, 2026David Courtis, Ting HuPersonality Mechanistic Interpretability
COCOLogic-V2: Identifying Logical Inconsistencies via Truly Hard-Negatives
Jun 26, 2026David Steinmann, Antonia Wüst, Kristian Kersting +1Visual Reasoning Interpretable Models
Autoencoder Architectures for Athlete Performance Scoring from Wearable Telemetry
Jun 26, 2026Mateusz Kubita, Jan Zubalewicz, Krzysztof SiwekMasked Autoencoders Sports Science
Can LLMs Judge Better Than They Generate? Evaluating Task Asymmetry, Mechanistic Interpretability and Transferability for In-Context QA
Jun 26, 2026Sambaran BandyopadhyaySelf-Assessments In-Context
The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching
Jun 25, 2026Sankaran Vaidyanathan, David Arbour, Aaron Mueller +2Causal Mediation Analysis Mechanistic Interpretability
PairSAE: Mechanistic Interpretability from Pair Representations in Protein Co-Folding
Jun 25, 2026Giosue Migliorini, Aristofanis Rontogiannis, Grigori Guitchounts +3Protein Data Bank Protein
LMs as Task-Specific Knowledge Bases: An Interpretability Analysis
Jun 25, 2026Amit Elhelo, Amir Globerson, Mor GevaModel Interpretability Chain-of-Thought Reasoning
Batch-Invariant Spectral Intelligence for Robust and Explainable Insect Authentication
Jun 25, 2026Majharulislam Babor, Giacomo Rossi, Annalisa Altavilla +2Bees Non-Destructive Frying Oil Oxidation Assessment
Radical AI Interpretability
Jun 25, 2026Daniel A. Herrmann, Benjamin A. LevinsteinTrustworthy Artificial Intelligence Mechanistic Interpretability
Interpreting "Interpretability" and Explaining "Explainability" in Machine Learning in Physics
Jun 24, 2026Rikab Gambhir, Luisa Lucie-Smith, Jesse ThalerModel Interpretability Explainability
Explainable Control Framework (XCF) based on Fuzzy Model-Agnostic Explanation and LLM Agent-Supported Interface
Jun 24, 2026Faliang Yin, Hak-Keung Lam, David WatsonAgentic Control Interpretable Models
Expresso-AI: Explainable Video-Based Deep Learning Models for Depression Diagnosis
Jun 24, 2026Felipe Moreno, Sharifa Alghowinem, Hae Won Park +1Depression Detection Depression
Beyond Shapley: Efficient Computation of Asymmetric Shapley Values
Jun 23, 2026Ezequiel Companeetz, Santiago Cifuentes, Sergio AbriolaShapley Value Interpretable Models
Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations
Jun 23, 2026Jonas Klotz, Cassio F. Dantas, Pallavi Jain +2Improving Sparse Autoencoders Semantic Representations
Don't Go Breaking My LLM: The Impact of Pruning Attention Layers on Explanation Faithfulness and Confidence Calibration
Jun 23, 2026Pietro Tropeano, Maria Maistro, Tuukka Ruotsalo +1Model Interpretability Explanation Faithfulness
Evidence for feature-specific error correction in LLMs
Jun 23, 2026Francisco Ferreira da Silva, Stefan HeimersheimLarge Language Model Performance Error Correction
Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models
Jun 23, 2026Cosimo Galeone, Anna Ettorre, Minsu Park +2Mechanistic Interpretability Model Activations
What Does a Pathological Speech Assessment Model Know about Acoustic Features? A Case Study on Oral and Oropharyngeal Cancer Patients
Jun 23, 2026Tuan Nguyen, Corinne Fredouille, Alain Ghio +2Wav2Vec Speaker Recognition
A Pāninian Foundation for Indic Language Processing
Jun 23, 2026Ritwik Banerjee, Lav R. VarshneyEnglish Model Interpretability
Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability?
Jun 23, 2026Ayan Antik Khan, Harsh Kohli, Yuekun Yao +2Mechanistic Interpretability Circuits
AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent
Jun 21, 2026Weidi Luo, Qiming Zhang, Yihao Quan +5Large Language Model Safety Safety
Performance and Interpretability of Convolutional, Transformer, and Hybrid Deep Learning Models in Colorectal Histology Classification
Jun 21, 2026Reza BozorgpourHybrid Transformer Computational Pathology
From Handcrafted Features to Functional Edge Learning: Evolution of EEG Seizure Detection Frameworks
Jun 20, 2026Sepideh Kheirollahi, Mohammad Rasoul RoshanshahInterictal Epileptiform Discharges Deep Learning
Interpreting Latent CoT Reasoning as Dynamical Systems
Jun 20, 2026Sabari Iyyappan Duraipandian, Shreya Sanjay Boyane, Manju Nagesh +3Efficient Latent Reasoning Model Interpretability
A Multi-Agent Audit Framework for High-Stakes Reasoning: Evaluation and Interpretability in Clinical Mental Health Screening
Jun 19, 2026Jingchen Ye, Yanpei Yu, Luyao ZhangClinical Reasoning Multi-Agent Large Language Model Systems
How Transparent is DiffusionGemma?
Jun 18, 2026Joshua Engels, Callum McDougall, Bilal Chughtai +11Transparency Interpretable Models
Critical Percolation as a Synthetic Data Model for Interpretability
Jun 18, 2026Aryeh Brill, Tom Ingebretsen CarlsonSynthetic Dataset Synthetic Data
Multimodal Concept Bottleneck Models
Jun 18, 2026Tongqing Shi, Ge Yan, Tuomas Oikarinen +1Concept Bottleneck Models Model Interpretability
Clusters are All You Need: Pre-Training the Tsetlin Machine with Semantic Clusters from Language Models for Interpretability
Jun 18, 2026Jiechao Gao, Rohan Kumar Yadav, Yuangang Li +4Bert-Based Models Model Interpretability
Comparing Linear Probes with Mahalanobis Cosine Similarity
Jun 17, 2026Zhuofan Josh Ying, Peter Hase, Nikolaus KriegeskorteCosine Similarity Model Interpretability
Concept Flow Models: Anchoring Concept-Based Reasoning with Hierarchical Bottlenecks
Jun 17, 2026Ya Wang, Adrian PaschkeClass-Incremental Concept Bottleneck Model Concept Bottleneck Models
Who Wins the Conflict? Mechanistic Interpretability of Text Bias in Audio LLMs
Jun 17, 2026Hyebin Cho, Suho Yoo, Jaehyuk Jang +2Large Audio Language Models Conflict
Closing the Loop: PID Feedback Control for Interpretable Activation Steering in Symbolic Music Generation
Jun 17, 2026Ioannis Prokopiou, Pantelis Vikatos, Maximos Kaliakatsos-Papakostas +2Activation Steering Music Generation
Bridging Data Gaps in Structural Fragility Modeling through Transfer Learning: Methodology and Case Studies
Jun 17, 2026Narges Saeednejad, Jamie Ellen PadgettFragility Transfer Learning
Effects of sparsity and superposition on loss in simple autoencoders
Jun 16, 2026Mriganka Basu Roy Chowdhury, Eric McLaughlin WeinerImproving Sparse Autoencoders Activation Functions
From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability
Jun 16, 2026Dibyanayan Bandyopadhyay, Asif EkbalModel Interpretability Model Activations
Can Physician Expertise Improve Machine Learning Identification of Delirium?
Jun 16, 2026Xinyu Qin, Vicky Ye, Ruiheng Yu +1Clinical Decision Support Interpretable Models
Scalable Circuit Learning for Interpreting Large Language Models
Jun 15, 2026Naiyu Yin, Dennis Wei, Tian Gao +3Mechanistic Interpretability Circuits
Demystifying Variance in Circuit Discovery of LLMs
Jun 15, 2026Frank Zhengqing Wu, Francesco Tonin, Volkan CevherMechanistic Interpretability Circuits
Scalable and Interpretable Representation Alignment with Ordinal Similarity
Jun 15, 2026Diogo Soares, Pankhil Gawade, Andrea Dittadi +1Semantic Similarity Metrics Representation Learning
Medical Heuristic Learning: An LLM-Driven Framework for Interpretable and Auditable Clinical Decision Rules
Jun 15, 2026Wei Xu, Ke Yang, Gang Luo +4Clinical Decision Support Interpretable Models
Circuit Tracing in Autoregressive Protein Language Models
Jun 14, 2026Darin Tsui, William Deinzer, Daniel Saeedi +1Mechanistic Interpretability Autoregressive Language Models
Trusting Right Predictions for Wrong Reasons: A LIME Based Analysis of Deep Learning Interpretability in Lung Cancer Diagnosis
Jun 14, 2026Samarpan Poudel, Vladislav D VekslerNon-Small Cell Lung Cancer Model Interpretability
The limits of interpretability in multiple linear regression
Jun 14, 2026Anand Sharma, Chen Liu, Daniele Coslovich +1Model Interpretability Logistic Regression
NeRD: Neuro-Symbolic Rule Distillation for Efficient Ontology-Grounded Chain-of-Thought in Medical Image Diagnosis
Jun 14, 2026Hongxi Yang, Yiwen Jiang, Siyuan Yan +8Model Interpretability Neuro-Symbolic Framework
Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning
Jun 13, 2026Ali Dasdan, Manan Shah, W. Russell Neuman +3Moral Reasoning Task Framing
Enhancing Precision Agriculture with a Hybrid Deep Learning Framework for Multi-Class Plant Disease Classification and Interpretability
Jun 13, 2026Hasibul Islam Sufi, Ridam Roy, Shayla Alam Setu +1Tomato Diseases Deep Learning Framework
Beyond Importance: Interchange-Sobol Sensitivity Reveals Task-Specific Content Channels in Transformer Components
Jun 12, 2026Yifeng Guo, Jin-Hong Du, Xiang ChenTransformer Architectures Importance

Jul 1, 2026 · cs.LGJ/K move · Enter open · S save

The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology

Andrzej Szablewski, Gabriel Konar-Steenberg, Raffaello Fornasiere, Nikita Menon+1

1LASR Labs

Model organisms (MOs) - language models trained to exhibit undesired or unnatural behaviours - are frequently used as testbeds for evaluating white-box interpretability techniques. Current MOs are typically constructed via post-hoc supervised fine-tuning (SFT) on behavioural transcripts or synthetic documents. Prior research has shown that interpretability methods can easily identify hidden behaviours in these MOs. However, recent work suggests that such post-hoc training methods may make interpretability unrealistically easy. We investigate this claim by constructing a suite of 54

\verb|OLMo2-1B|

- and

\verb|gemma-3-1b-it|

-based MOs trained with seven different techniques, including standard post-hoc SFT, post-hoc DPO, and more realistic integration of MO data into the OLMo post-training DPO phase. We use these MO variants to benchmark activation oracles, activation steering, logit lens, and sparse autoencoders. Our findings show that (i) MO interpretability depends strongly on training objective, target behaviour, model architecture, and training data generation pipeline; (ii) substantial variance remains even after controlling for differences in the strength of target behaviour expression; and (iii) our more realistic

\textit{integrated training}

often yields less interpretable MOs than standard post-hoc methods. Our results cast substantial doubt on the validity of current MOs as interpretability proxies.

Model Interpretability Model Activations Post-Hoc Lotteries

Open paper Ask about it PDF