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 2026-09-14

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 Methods

Within Mechanistic Interpretability

262 papersExplore

Focused topic

Mechanistic Interpretability

Within Mechanistic Interpretability

154 papersExplore

Focused topic

Interpretable Machine Learning

Within Mechanistic Interpretability

55 papersExplore

434 papers

Latest in Mechanistic Interpretability

Open your feed →

Explainable Prediction from Mobile Sensing Data through LLM-guided Concept Integration
Sep 14, 2026Yuning Wang, Iman Azimi, Amir M. Rahmani +1Clinical Prediction Interpretable Machine Learning
MAxBench: A Multinomial Concept Recovery Benchmark
Sep 14, 2026Divya Appapogu, Freya Behrens, Yonatan Belinkov +1Model Interpretability Methods
XAI-Arena: Can LLMs Assess the Quality of XAI Explanations?
Sep 10, 2026Yanfei Hu Fleischhauer, Alona Zharova, Nadja Klein +1Xai Explainable Artificial Intelligence
Auditable Emergency Triage for Maternal and Newborn Care in India
Sep 10, 2026Shobhit Jagga, Aman Dalmia, Niharika Priyadarshini +7Triage Model Interpretability Methods
An Explainable Machine Learning Framework for Predicting Blood-Brain Barrier Permeability Using Molecular Descriptors
Sep 9, 2026Fatemeh MahmoudiMolecular Descriptors Molecular Structure Elucidation
Do Reasoning Representations Help Humans Evaluate LLM Outputs?
Sep 8, 2026Jaewoo Lim, Sungbok Shin, Sanghyun HongLLM Reasoning Methods Model Interpretability Methods
GraphFAS: A Distributed System for Automated Graph Feature Generation and Selection in Industrial Transaction Networks
Sep 8, 2026Yice Luo, Yun Zhu, Xi Chen +7Fraud Detection Model Interpretability Methods
Beliefs and Behavior in Language Models
Sep 7, 2026Alex Smolin, Bryan WilderLarge Language Model Reliability Belief
LLM Layers Immediately Correct Each Other
Sep 7, 2026Arjun Patrawala, Jiahai Feng, Erik Jones +1Model Activations Residual Stream
On the Recall Scaling Laws in Mamba: A Theoretical and Mechanistic Study via Hashing
Sep 7, 2026Yuval Koren, Assaf Ben-Kish, Raja Giryes +2Associative Memory Factual Recall
When Superpixels Fail on Documents: A Study of Segmentation for LIME Explanations
Sep 7, 2026Quentin Telnoff, Emanuela Boros, Mickaël Coustaty +3Concept-Based Explainability Document
Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning
Sep 3, 2026Kevin Du, Alexander Hoyle, Laura Ruis +1Reasoning Chain Reasoning Traces
Witnesses Explain Anomalies
Sep 3, 2026Lamine DiopAnomaly Score Anomaly
Large Language Models in Resolving Contextual Knowledge Conflicts
Sep 2, 2026Xinye Yang, Zhenyang Liu, Ruisi Li +1Conflict Mechanistic Interpretability
ObserverBench: Testing Mechanistic Estimates for Intervention and Control
Sep 2, 2026Vijay ErramilliMechanistic Interpretability Causal Intervention
Towards reliable multimodal disaster severity assessment through preference optimization and explainable vision-language reasoning
Sep 1, 2026Yuanjun Zhang, Fuzel Ahamed Shaik, Suvojit Acharjee +2Post-Disaster Damage Assessment Disasters
S^3martCirc: Self-supervised Smart Circuit Discovery
Sep 1, 2026Wendy Zheng, Yinhan He, Liang Wu +1Mechanistic Interpretability Circuits
MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines
Aug 31, 2026Alireza Bayat Makou, Emirhan Böge, Phu Gia Hoang +5Model Interpretability Methods Mechanistic Interpretability
The Safety Relay in Roleplay Jailbreaks: A Component-Resolved Causal Analysis of Harm Recognition and Refusal
Aug 31, 2026Md Mokarram Chowdhury, Ernie Chang, Yang LiJailbreaks Refusals
Tensor Methods for Language Models: From Token Representation to Training, Adaptation, Inference, Compression, and Interpretability
Aug 31, 2026Matvei Tarasov, Salman Ahmadi-Asl, Andre L. F. de Almeida +1Large Language Model Scale Tensor
TabSOM: A tabular-to-image encoding method based on self-organizing maps
Aug 13, 2026David Chushig-Muzo, María Ángeles Rodríguez de Cara, Eva Milara +3Tabular Learning Model Interpretability Methods
Decoding Task Progress from VLA Representations
Aug 13, 2026Atiksh Bhardwaj, Edward Weiyi Duan, Prithwish Dan +2Vision-Language-Action Visuomotor Policy
Perturbation-based Regional Interpretability through Subtraction Mapping (PRISM): naming-error dissociations in language models and post-stroke aphasia
Aug 13, 2026Xiang Guan, Roger D. Newman-Norlund, Yong Yang +8Dysarthric Speech Linguistics
Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
Aug 12, 2026Mengru Wang, Junfeng Fang, Shuofei Qiao +16Artificial Intelligence Safety Artificial Intelligence Scientists
HyperANFIS: Enhancing Rule Representation and Interpretability in Adaptive Neuro-Fuzzy Systems via Hyperbolic Geometry
Aug 12, 2026Haoran Pei, Zhao Su, Zetao Lin +6Hyperbolic Space Model Interpretability Methods
Causal Structure is Inducible but Functionally Decoupled: The Routing/Readout Boundary of a Typed Mechanism Library
Aug 12, 2026Xining XunCausal Structure and Reasoning Mechanistic Interpretability
From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop
Aug 11, 2026Rahul Gupta, Abhinav Mohanty, Anaelia Ovalle +10Large Language Model Reliability Model Interpretability Methods
Measuring Semantic Abstractness of SAE Features via Nonlocality
Aug 11, 2026Chuqiao Lin, Shivaji Sondhi, Xiao-Liang QiSparse Autoencoders Mechanistic Interpretability
Conversational versus Dashboard Explainable AI for UAV Intrusion Detection: An Empirical Study of Operator Trust and Reliance
Aug 11, 2026Cong Chi Nguyen, Trang Mai Xuan, Vu-Duc Ngo +3Unmanned Aerial Vehicle Tracking Intrusion Detection
Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability
Aug 10, 2026Ashim Dhor, Pin-Yu ChenMechanistic Interpretability Model Interpretability Methods
Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
Aug 10, 2026Kevin MurphyAgentic Discovery Structural Causal Model
Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways
Aug 10, 2026Shuyi Miao, Wangjie Qiu, Pengyang Shao +4Multilingual Safety Large Language Model Alignment
Multilingual Emotion Neurons in Large Audio-Language Models
Aug 9, 2026Xiutian Zhao, Philipp Koehn, Björn Schuller +1Large Audio Language Models Protein Language Model
The Spectral Neuron
Aug 8, 2026Alex ShtoffModel Interpretability Methods Affine
Beyond the Black Box: Interpretable Models of Human Randomisation Failures
Aug 7, 2026Ngoc Linh DaoInterpretable Machine Learning Generalizable Time-Series Behavioral Modeling
Transformer Geometry Observatory TGO-IV: Developmental Topology Observatory
Aug 7, 2026Kaustubh Kapil, Kishor P. UplaVisual Geometry Grounded Transformer Topology
Interpretable reinforcement learning with decision-tree pruning
Aug 7, 2026Mark Leon Ringer, Michel TokicSafe Reinforcement Learning Model Interpretability Methods
Finding Usable Weight Mechanisms with Tiled SVD
Aug 7, 2026Ash Manvi, Samreena TajreenModel Weights Singular Value Decomposition
Faster Query-Key Learning Sharpens Attention in Self-Attention Models
Aug 7, 2026Rahul Vashisht, Harish G. RamaswamySelf-Attention Mechanism Learning Rates
MI-MIDI: Mechanistic Interpretability of Text-to-MIDI Generation Models via Probing, Lenses and Steering
Aug 6, 2026Jakub Poćwiardowski, Mateusz ModrzejewskiGenerative Music Models Music Generation
Scaling Inherently Interpretable Language Models
Aug 6, 2026Guide Labs Team, Andreas Madsen, Aya Abdelsalam Ismail +7Model Interpretability Methods Diffusion Language Models
Sparse Weight Decomposition for Efficient Circuit Extraction
Aug 4, 2026Chuanhao Yan, Xuhan Huang, Yawen Duan +4Model Weights Circuits
Interpretable Machine Learning for Traffic Congestion Prediction: Unveiling the Impact of Different COVID-19 Periods
Aug 2, 2026Dan Zhu, Chi Sin Ng, Litian Xie +1Accurate Traffic Forecasting Coronavirus Disease
Interpretable machine learning for predicting splitting strength of asphalt concrete: insights from SHAP analysis
Aug 2, 2026Jianglei Xing, Xiao Tan, Dongzhao Jin +3Shapley Value Interpretable Machine Learning
xMICD: Explainable Representation of Multiple ICD Codes
Aug 2, 2026Pat Vatiwutipong, Kumkup Keeratisiwakul, Albert Phuoc Kien Van Truong +4International Classification Of Disease Codes Interpretable Machine Learning
DiffuseAgent-MI: Distributionally-Grounded,Tool-Integrated Self-Evolving Agents for Faithful Visual Reasoning
Aug 1, 2026An Lanji, Dawei Liu, Jin Li +3Visual Reasoning Mechanistic Interpretability
Persistent Convolution: A Topological Framework for AI Alignment Testing and Semantic Space Characterization
Jul 31, 2026Tyler Ashoff, Jordan RoduArtificial Intelligence Alignment Artificial Intelligence Benchmarks
Search Strategies for Optimal Classification and Regression Trees
Jul 30, 2026Jacobus G. M. van der Linden, Mim van den Bos, Emir DemirovićDecision Trees Random Forest
HealthCAT: An Interpretable Encoder-only Transformer Framework for Health Indicator Prediction and Temporal Interpretation of Wearable Sensor Data
Jul 30, 2026Xiaotong Yu, Joshua Y. Kim, HaeJin Lee +1Wearable Devices Transformer Encoder
Expanding Data-Agnostic Pivotal Instances Selection Models with Proximity Trees and Ensemble Learning
Jul 29, 2026Alessio Cascione, Mattia Setzu, Cristiano Landi +2Interpretable Machine Learning Decision Trees
ECG-InterpBench: Benchmarking the Interpretability of ECG Foundation Models with Matched-Scale Sparse Autoencoders
Jul 29, 2026Yixuan Duan, Wei QiuEcg-Specific Augmentations Electronic Health Record Foundation Models
Emergent Latent-State Computation under Stochastic Volatility
Jul 28, 2026Xiaoyu Huang, Lulu WangIntermediate Latent States Latent States
KANEx: Translating Kolmogorov-Arnold Networks' Interpretability to Medical Explainability
Jul 27, 2026Krithi Shailya, Ananya Lakshmi Ravi, Venkatanathan K. V. +4Concept-Based Explainability Medical Vision-Language Models
Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects
Jul 27, 2026Phu Gia Hoang, Anwoy Chatterjee, Tanmoy Chakraborty +2Improving Sparse Autoencoders Sparse Autoencoders
LEX-EC: A Lexical Evidence-Channel Audit Framework for Zero-Shot LLM Personality Classification in Black-Box Settings
Jul 27, 2026Brittany Harbison, Ashok K. GoelPersonality Large Language Model Bias
Do LLMs Know Their Vulnerable Scenarios?
Jul 26, 2026Ziheng Peng, Huiqi Deng, Haoran Jing +5Large Language Model Safety Vulnerable Code
LAWFUL: Law-Aligned Witness for Faithful Use of Latents
Jul 26, 2026Kevin Chen, Kenneth W. Parker, Anish AroraModel Interpretability Methods Physics-Aware Models
Continuous surrogates versus threshold Boolean networks for modeling Arabidopsis ISR gene regulation
Jul 25, 2026Gonzalo A. RuzRegulatory Networks Surrogate Modeling
Through the Bottleneck: How Multi-head Latent Attention Separates Content from Position in Language Models
Jul 25, 2026Dhruvil S, Fenil Sojitra, Ravirajsinh ChauhanMulti-Head Attention Deepseek-R1
Same Predictions, Different Reasons: The Effect of Quantization on Model Explanations
Jul 24, 2026Kazi Kamruzzaman Rabbi, Md. Zami Al Zunaed Farabe, M. Sohel RahmanPost-Training Quantization Quantization Effects

Sep 14, 2026 · cs.LGJ/K move · Enter open · S save

Explainable Prediction from Mobile Sensing Data through LLM-guided Concept Integration

Yuning Wang, Iman Azimi, Amir M. Rahmani, Pasi Liljeberg

Mobile sensing enables longitudinal monitoring of behavioral and physiological patterns in everyday settings. However, accurate prediction remains challenging in small-cohort health-sensing studies, where task-specific outcome supervision is limited relative to heterogeneous sensing data. Interpretability is also important, as model outputs should reflect meaningful behavioral and physiological patterns rather than predictive scores alone. We develop a Concept-Integrated Transformer (CIT) with LLM-guided concept supervision for explainable prediction from mobile sensing data. CIT uses a pretrained large language model to generate baseline-aware concept abnormality targets with confidence weights without manual concept annotation. Across two longitudinal datasets, CIT achieves the highest F1 score on AFFECT (0.756) and ties for the highest on a PHQ-9 dataset (0.765). The learned concept scores also reveal interpretable behavioral and physiological patterns; in AFFECT, sleep quantity and quality show the clearest difference between high and low negative affect groups. These findings support LLM-guided concept integration for accurate and interpretable prediction in small-cohort mobile sensing studies.

Clinical Prediction Interpretable Machine Learning Generalizable Time-Series Behavioral Modeling

Open paper Ask about it PDF