# Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance

arXiv: https://arxiv.org/abs/2605.31304 · HTML: https://mlsanity.com/paper/2605.31304/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 65 of its 77 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 30 of 65)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://mlsanity.com/paper/2106.10270/) (2021)
- [Scaling and evaluating sparse autoencoders](https://mlsanity.com/paper/2406.04093/) (2024)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [A Survey on Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2402.00253/) (2024)

## Abstract (arXiv)

Deep neural networks (DNNs) are widely used, but interpreting what they actually learn remains difficult. A major obstacle is that individual neurons often encode multiple unrelated concepts, obscuring the decision process of the network. While prior work, such as sparse autoencoders, can separate these mixed signals into more meaningful, "monosemantic" features, this typically requires altering the model in ways that can degrade downstream performance. To overcome this, we introduce ELUDe (explicit, lossless, unsupervised disentanglement), a method for improving the interpretability of DNNs while preserving their functional equivalence. ELUDe breaks latent representations into clear, inspectable sub-units that behave like interpretable features, while guaranteeing that the model's outputs remain exactly the same. It requires no explicit training, no labels, and can be applied to pretrained models. ELUDe works by reorganizing how information flows between layers, re-routing concept-specific contributions while preserving the original computation by construction. Across several vision models, including DINOv2 and supervised ViT-B/16, ELUDe improves interpretability, keeps downstream accuracy unchanged, runs efficiently, and supports practical uses such as steering model representations. In short, ELUDe offers interpretability (almost) without a tradeoff: clearer, scalable, and actionable model insights with no loss in performance.