# ConceptLens: from Pixels to Understanding

arXiv: https://arxiv.org/abs/2410.05311 · HTML: https://mlsanity.com/paper/2410.05311/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 11 references that are in the map.
- First posted on arXiv 4 Oct 2024.

## Builds on (most cited first, 4 of 4)

- [CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks](https://mlsanity.com/paper/2204.10965/) (2022)
- [Efficient Concept Induction for Description Logics](https://mlsanity.com/paper/1812.03243/) (2018)
- [On the Value of Labeled Data and Symbolic Methods for Hidden Neuron Activation Analysis](https://mlsanity.com/paper/2404.13567/) (2024)
- [Error-margin Analysis for Hidden Neuron Activation Labels](https://mlsanity.com/paper/2405.09580/) (2024)

## Abstract (arXiv)

ConceptLens is an innovative tool designed to illuminate the intricate workings of deep neural networks (DNNs) by visualizing hidden neuron activations. By integrating deep learning with symbolic methods, ConceptLens offers users a unique way to understand what triggers neuron activations and how they respond to various stimuli. The tool uses error-margin analysis to provide insights into the confidence levels of neuron activations, thereby enhancing the interpretability of DNNs. This paper presents an overview of ConceptLens, its implementation, and its application in real-time visualization of neuron activations and error margins through bar charts.