Topographic Training Concentrates Causal Circuits Without Improving Neuron Monosemanticity

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.

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.

How interpretable are the features of leading vision models? The question is increasingly pressing as these models move from research benchmarks into high-stakes deployments, yet existing methods cannot answer it reliably. We close this gap with a framework for measuring and comparing the human interpretability of vision models, built around two complementary psychophysics protocols: (1) localizability -- can an observer predict where a feature fires on a novel image? -- and (2) nameability -- can an observer accurately describe what the feature represents? Features are recovered via sparse autoencoders, and a chance-anchored scoring function places every model on a common scale. Applying the framework to six vision transformers -- two supervised ViTs and four foundation models (DINOv2, DINOv3, CLIP, SigLIP) -- we collected more than $15{,}000$ behavioral responses, analyzing the $13{,}400$ responses from the $377$ participants who passed our pre-specified quality checks. Foundation models are consistently less interpretable than their supervised counterparts, and the gap is not a capability tradeoff: interpretability does not correlate with downstream task performance on any benchmark we examine. What does correlate is the locality of a feature's activations and coarse-grained semantic alignment with humans -- models with focal activations and representations that reflect the world's broad categorical structure produce more interpretable features, whereas fine-grained perceptual alignment does not. The two protocols yield strongly correlated rankings and share the same predictors, establishing interpretability as an independent, measurable dimension of representation quality -- and, surprisingly, one on which every foundation model we tested falls below the supervised baselines that came before. Capability alone cannot close that gap; locality and coarse-grained alignment can.