cs.CVSep 8, 2026

"World Knowledge" in the Weights: Reading Concept Circuits of Vision Transformers

Authors: Yanlin Chen, Tang Li, Xi Peng

Abstract

Vision transformers (ViTs) have achieved remarkable generalization across visual domains, yet little is known about how they internally represent the structure of the world. To address this gap, we use Cross-Layer Transcoders (CLTs) to read concept circuits from ViTs: directed graphs whose nodes correspond to sparse, interpretable concepts and edges capture concept interactions across layers. Our method yields two complementary views of model behavior. The global concept circuit is input-invariant and can be recovered directly from learned cross-layer weights, exposing the reusable "world knowledge" encoded in the model. The instance concept circuit is input-dependent and identifies the concepts and pathways actually used for a specific prediction, enabling faithful example-level explanations. We demonstrate the utility of concept circuits in three ways: (1) Automatic spurious correlation discovery: leveraging the statistics of our global concept circuits to identify shortcut dependencies within the model. (2) Spurious correlation removal: intervening on the instance concept circuit to steer the model towards correct predictions. Empirical results show that our method outperforms existing counterparts by 11.0% on the Waterbird dataset. (3) Model comparison: contrasting the global concept circuits of different foundation models (e.g., CLIP vs. DINO) to reveal how supervision paradigms shape representational structure. Our code is available at https://github.com/deep-real/VisionCLT

Explore similar work

CardsList
Jun 4, 2026cs.CV

Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers

Despite high accuracy, Vision Transformer (ViT) predictions can be driven by spurious cues, raising the need to understand their inner workings before safe deployment. Sparse autoencoders (SAEs) provide a promising lens for decomposing model representations into human-interpretable concepts, yet adapting SAE-based interpretation to ViTs remains challenging due to limited control over concept coverage and subjective, non-scalable feature interpretation. To fill the gaps, motivated by neuroscience-inspired principles, we propose ViSAE, a mechanistic interpretability toolbox for understanding ViT inner workings through concept circuits. ViSAE consists of three components: (1) A probing suite with 64K images and a 16K visually grounded concept vocabulary, improving concept coverage efficiency by 20x over ImageNet and interpretation accuracy by 28.7% over existing concept sets. (2) Top-down concept reading and Bottom-up circuit tracing algorithms that automatically recover ViT inner workings via concept circuits. (3) Applications for auditing and steering ViT behavior. Through concept editing, ViSAE improves the worst-group accuracy on WaterBirds by 48.2%, outperforming existing methods by 23.8%. Our data and code: https://github.com/deep-real/ViSAE.
Tang Li, Yanlin Chen, Mengmeng Ma +1
Self-Supervised Vision TransformersVision TransformerMechanistic InterpretabilityVisual ReasoningVistaCircuits
AskPDF
Apr 25, 2026cs.CV

From Edges to Depth: Probing the Spatial Hierarchy in Vision Transformers

Vision Transformers trained only on image classification routinely transfer to tasks that demand spatial understanding, yet they receive no spatial supervision during pretraining. We ask where and how robustly such structure is encoded. Probing a frozen ViT-B/16 layerwise for two complementary properties, local patch boundaries (BSDS500) and per-patch depth (NYU Depth V2), reveals a clear hierarchy: boundary structure becomes linearly decodable at layers 5-6 (AP = 0.833), while depth, which requires integrating global cues, peaks two to three layers later at layer 8 (MAE = 0.0875). Both signals collapse at the final classification layer, and random-weight controls confirm the encodings are learned rather than architectural. Causal interventions add specificity: ablating the single direction a linear depth probe reads degrades depth decoding by up to 165%, while ablating any other direction changes it by less than 1%. Targeted activation patching along that direction shows the depth signal is partially re-derived at each layer rather than passively carried in the residual stream, with mid-layer interventions persisting most strongly downstream. The result is that a classification-trained ViT develops an actively maintained spatial hierarchy that mirrors the early-to-late progression observed in the primate visual cortex.
Jainum Sanghavi
Self-Supervised Vision TransformersVision TransformerVisual PerceptionSpatial ReasoningHuman Visual CortexHierarchical+1
AskPDF
Aug 8, 2026cs.CV

Circuit Fine-Tuning for Compute-Efficient Transformer Adaptation

Parameter-Efficient Fine-Tuning (PEFT) has become the de facto standard for adapting Vision Transformers (ViTs) to downstream tasks. While parameter count has been the dominant efficiency metric in PEFT, it does not imply \textit{compute efficiency}: parameter-sparse methods can still incur full-model training cost per step, and typically need long schedules to reach peak accuracy. We introduce Circuit Fine-Tuning (CFT), a compute-efficient framework that uses circuit discovery---conventionally used to explain trained models---to select modules for fine-tuning before training. Whereas attribution is conventionally formulated against a trained task head, we formulate it against a near-zero-initialized probe head, which isolates the response of the backbone to the target distribution rather than the preferences of a particular classifier. CFT then fine-tunes only the recovered subgraph. CFT needs no learning-rate warmup and reaches peak accuracy in ∼20{\sim}20 epochs on average---versus 4444--9696 for strong PEFT baselines---yielding 2.32.3--6.6×6.6\times fewer training FLOPs and up to 16×16\times less wall-clock time, while adding zero parameters and no inference operations. Experiments across a standard visual transfer benchmark (VTAB-1k), hierarchical backbones (Swin), domain-shifted medical imaging (CBIS-DDSM), and a vision-language model (Gemma-3 on CUB-200) demonstrate the effectiveness of CFT. Code is available at https://github.com/UriKialy/CFT
Uri Z. Kialy, Gil Ben-Artzi
Parameter-Efficient Fine-TuningSelf-Supervised Vision TransformersVision TransformerContinual Fine-TuningCircuits
AskPDF