{"total":9,"rows":[{"id":"2510.11709","title":"Adversarial Attacks Leverage Interference Between Features in Superposition","created":"2025-10-13","cited_by_count":8,"area":null},{"id":"2509.06938","title":"From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers","created":"2025-09-08","cited_by_count":4,"area":null},{"id":"2512.09730","title":"Interpreto: An Explainability Library for Transformers","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2507.19420","title":"CircuitProbe: Tracing Visual Temporal Evidence Flow in Video Language Models","created":"2025-07-25","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":"2606.16196","title":"When Confidence Lacks Concepts: Interpretable OOD Detection via Representation Perturbations","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.28399","title":"Meta-learning as a principle for human-like visual representations","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2608.05122","title":"IRIS: A Visual Cortex-Inspired Framework for Analyzing Orientation Selectivity in Vision Transformers","created":"2026-08-05","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}],"next_cursor":null}