# Unsupervised decoding of encoded reasoning using language model interpretability

arXiv: https://arxiv.org/abs/2512.01222 · HTML: https://mlsanity.com/paper/2512.01222/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 20 of its 27 references that are in the map.
- First posted on arXiv 1 Dec 2025.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)
- Mechanistic interpretability / [Knowledge and representations inside LLMs](https://mlsanity.com/mechinterp/knowledge-and-representations-inside-llms/)

## Builds on (most cited first, 20 of 20)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach](https://mlsanity.com/paper/2502.05171/) (2025)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [Do Llamas Work in English? On the Latent Language of Multilingual Transformers](https://mlsanity.com/paper/2402.10588/) (2024)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [LlamaFirewall: An open source guardrail system for building secure AI agents](https://mlsanity.com/paper/2505.03574/) (2025)
- [Secret Collusion among AI Agents: Multi-Agent Deception via Steganography](https://mlsanity.com/paper/2402.07510/) (2024)
- [When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors](https://mlsanity.com/paper/2507.05246/) (2025)
- [The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities](https://mlsanity.com/paper/2411.04986/) (2024)
- [Preventing Language Models From Hiding Their Reasoning](https://mlsanity.com/paper/2310.18512/) (2023)
- [Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs](https://mlsanity.com/paper/2410.03768/) (2024)
- [Large language models can learn and generalize steganographic chain-of-thought under process supervision](https://mlsanity.com/paper/2506.01926/) (2025)
- [Early Signs of Steganographic Capabilities in Frontier LLMs](https://mlsanity.com/paper/2507.02737/) (2025)
- [The Steganographic Potentials of Language Models](https://mlsanity.com/paper/2505.03439/) (2025)

## Built on by (most cited first, 4 of 4)

- [Verbalizable Representations Form a Global Workspace in Language Models](https://mlsanity.com/paper/2607.15495/) (2026)
- [Not All LLM Reasoning is Visible in the Chain-of-Thought](https://mlsanity.com/paper/2607.22925/) (2026)
- [From Latent Signals to Reflection Behavior: Tracing Meta-Cognitive Activation Trajectory in R1-Style LLMs](https://mlsanity.com/paper/2602.01999/) (2026)
- [Stress-Testing Alignment Audits With Prompt-Level Strategic Deception](https://mlsanity.com/paper/2602.08877/) (2026)

## Abstract (arXiv)

As large language models become increasingly capable, there is growing concern that they may develop reasoning processes that are encoded or hidden from human oversight. To investigate whether current interpretability techniques can penetrate such encoded reasoning, we construct a controlled testbed by fine-tuning a reasoning model (DeepSeek-R1-Distill-Llama-70B) to perform chain-of-thought reasoning in ROT-13 encryption while maintaining intelligible English outputs. We evaluate mechanistic interpretability methods--in particular, logit lens analysis--on their ability to decode the model's hidden reasoning process using only internal activations. We show that logit lens can effectively translate encoded reasoning, with accuracy peaking in intermediate-to-late layers. Finally, we develop a fully unsupervised decoding pipeline that combines logit lens with automated paraphrasing, achieving substantial accuracy in reconstructing complete reasoning transcripts from internal model representations. These findings suggest that current mechanistic interpretability techniques may be more robust to simple forms of encoded reasoning than previously understood. Our work provides an initial framework for evaluating interpretability methods against models that reason in non-human-readable formats, contributing to the broader challenge of maintaining oversight over increasingly capable AI systems.