{"total":27,"rows":[{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2601.04480","title":"When Models Manipulate Manifolds: The Geometry of a Counting Task","created":"2026-01-08","cited_by_count":46,"area":null},{"id":"2411.17673","title":"SketchAgent: Language-Driven Sequential Sketch Generation","created":"2024-11-26","cited_by_count":31,"area":null},{"id":"2510.13900","title":"Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences","created":"2025-10-14","cited_by_count":28,"area":null},{"id":"2512.15712","title":"Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants","created":"2025-12-17","cited_by_count":12,"area":null},{"id":"2505.11770","title":"Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors","created":"2025-05-17","cited_by_count":11,"area":null},{"id":"2410.13569","title":"Learning on Model Weights using Tree Experts","created":"2024-10-17","cited_by_count":7,"area":null},{"id":"2510.07115","title":"Enhancing Concept Localization in CLIP-based Concept Bottleneck Models","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2410.02472","title":"Meta-Models: An Architecture for Decoding LLM Behaviors Through Interpreted Embeddings and Natural Language","created":"2024-10-03","cited_by_count":5,"area":null},{"id":"2512.08560","title":"BrainExplore: Large-Scale Discovery of Interpretable Visual Representations in the Human Brain","created":"2025-12-09","cited_by_count":5,"area":null},{"id":"2504.20902","title":"Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers","created":"2025-04-29","cited_by_count":4,"area":null},{"id":"2505.17425","title":"Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2603.07343","title":"Learning Concept Bottleneck Models from Mechanistic Explanations","created":"2026-03-07","cited_by_count":4,"area":null},{"id":"2607.18237","title":"The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric","created":"2026-07-20","cited_by_count":3,"area":null},{"id":"2411.15605","title":"GIFT: A Framework Towards Global Interpretable Faithful Textual Explanations of Vision Classifiers","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2411.18651","title":"Verbalized Representation Learning for Interpretable Few-Shot Generalization","created":"2024-11-27","cited_by_count":2,"area":null},{"id":"2510.06378","title":"Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2510.21704","title":"Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2606.03990","title":"Neuron Populations Exhibit Divergent Selectivity with Scale","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2603.24953","title":"Select, Hypothesize and Verify: Towards Verified Neuron Concept Interpretation","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.08039","title":"LINE: LLM-based Iterative Neuron Explanations for Vision Models","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.22477","title":"Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2606.19882","title":"Multimodal Concept Bottleneck Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2608.16251","title":"SCOUT: Semantic Concept Discovery for Open-Vocabulary Editing of face Recognition Templates","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.11860","title":"Explainability Assistant: A Conversational XAI Interface for Interpreting Energy Consumption Models","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.34030","title":"Uncovering shortcut learning in audio classifiers by discovering recurring concepts in temporal explanations","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.01870","title":"From Pixels to Policy: A Multi-Agent System for Intervention and Geo-Spatial Decision Support","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}