# One Lens, Many Worlds : A Capability-Typed Interface for World-Model Interpretability

arXiv: https://arxiv.org/abs/2606.09936 · HTML: https://mlsanity.com/paper/2606.09936/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 10 of its 66 references that are in the map.
- First posted on arXiv 7 Jun 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)
- Mechanistic interpretability / [Interpreting time-series and weather models](https://mlsanity.com/mechinterp/interpreting-time-series-and-weather-models/)

## Builds on (most cited first, 10 of 10)

- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [Scaling and evaluating sparse autoencoders](https://mlsanity.com/paper/2406.04093/) (2024)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [Localizing Model Behavior with Path Patching](https://mlsanity.com/paper/2304.05969/) (2023)
- [Improving Dictionary Learning with Gated Sparse Autoencoders](https://mlsanity.com/paper/2404.16014/) (2024)
- [NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals](https://mlsanity.com/paper/2407.14561/) (2024)

## Built on by (most cited first, 1 of 1)

- [RolloutFaith: Auditing Persistent Internal Interventions in Visual World Model](https://mlsanity.com/paper/2609.36843/) (2026)

## Abstract (arXiv)

World models are now built on substantially different computational substrates. Latent recurrent state-space models such as PlaNet and the Dreamer family compress observations into recurrent states; token-based models such as IRIS quantize observations into a learned codebook and predict autoregressively with a transformer; and joint-embedding predictive architectures such as I-JEPA predict in a learned latent space with no pixel decoder. The interpretability methods applied to these models, including probing, activation patching, sparse autoencoders, and surprise analysis, share a common set of primitives, yet they are re-implemented from scratch for each architecture because existing hook-and-cache tooling assumes a transformer language model with no notion of actions, environment steps, or imagined rollouts. We argue that this fragmentation reflects the tooling rather than the models, and that the shared structure of world models is captured by a small typed interface. We present WorldModelLens, an open-source interpretability substrate organized around a capability-typed adapter: every model implements four required methods (encode, transition, initial state, sample) and declares a set of optional heads (decode, reward, continue, actor, critic) through an explicit capability descriptor, so that reinforcement-learning and self-supervised world models are first-class without either imitating the other. A single hook and cache layer exposes time-indexed activations, imagination rollouts, and intervention replay over this interface, allowing each analysis to be written once.