# Transcoders for Investigating Deception in Language Models

arXiv: https://arxiv.org/abs/2607.14791 · HTML: https://mlsanity.com/paper/2607.14791/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Probing deception, bias and beliefs, one of 13 directions in Mechanistic interpretability.
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Placed in

- Mechanistic interpretability / [Probing deception, bias and beliefs](https://mlsanity.com/mechinterp/probing-deception-bias-and-beliefs/)

## Builds on (most cited first, 11 of 11)

- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Transcoders Find Interpretable LLM Feature Circuits](https://mlsanity.com/paper/2406.11944/) (2024)
- [Truth is Universal: Robust Detection of Lies in LLMs](https://mlsanity.com/paper/2407.12831/) (2024)
- [Detecting Strategic Deception Using Linear Probes](https://mlsanity.com/paper/2502.03407/) (2025)
- [Transcoders Beat Sparse Autoencoders for Interpretability](https://mlsanity.com/paper/2501.18823/) (2025)
- [When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models](https://mlsanity.com/paper/2506.04909/) (2025)
- [Exploiting Large Language Models (LLMs) through Deception Techniques and Persuasion Principles](https://mlsanity.com/paper/2311.14876/) (2023)
- [Detecting and Understanding Vulnerabilities in Language Models via Mechanistic Interpretability](https://mlsanity.com/paper/2407.19842/) (2024)
- [Revisiting End-To-End Sparse Autoencoder Training: A Short Finetune Is All You Need](https://mlsanity.com/paper/2503.17272/) (2025)
- [Banal Deception Human-AI Ecosystems: A Study of People's Perceptions of LLM-generated Deceptive Behaviour](https://mlsanity.com/paper/2406.08386/) (2024)
- [Evaluating the Evaluators: Trust in Adversarial Robustness Tests](https://mlsanity.com/paper/2507.03450/) (2025)

## Abstract (arXiv)

Transcoders have recently emerged as a promising approach for mechanistic interpretability (MI), enabling circuit-level analysis of model behaviour. In this paper, we investigate the use of transcoders to analyse deceptive behaviour in language models, a behaviour that poses a safety and security risk. Using a Qwen3-4B model with pre-trained transcoders, specifically per-layer transcoders (PLTs), we construct attribution graphs that capture feature activations and inter-feature dependencies, allowing circuit-level analysis of deception. Through feature steering and circuit analysis, we identified a dictionary of deception-related features and show that these features exert a stronger influence on deceptive outputs, as they produce predictable shifts between deceptive and non-deceptive responses. These findings suggest that deception emerges from internal model mechanisms and highlight the potential of transcoders for behavioural monitoring and early detection of security vulnerabilities related to malicious behaviours in language models.