# Mechanistic Interpretability of Cognitive Complexity in LLMs via Linear Probing using Bloom's Taxonomy

arXiv: https://arxiv.org/abs/2602.17229 · HTML: https://mlsanity.com/paper/2602.17229/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge and representations inside LLMs, one of 13 directions in Mechanistic interpretability.
- Builds on 24 of its 46 references that are in the map.
- First posted on arXiv 19 Feb 2026.

## Placed in

- Mechanistic interpretability / [Knowledge and representations inside LLMs](https://mlsanity.com/mechinterp/knowledge-and-representations-inside-llms/)

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models](https://mlsanity.com/paper/2407.02646/) (2024)
- [A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models](https://mlsanity.com/paper/2503.05613/) (2025)
- [Linear Representations of Political Perspective Emerge in Large Language Models](https://mlsanity.com/paper/2503.02080/) (2025)
- [Towards Uncovering How Large Language Model Works: An Explainability Perspective](https://mlsanity.com/paper/2402.10688/) (2024)
- [Towards eliciting latent knowledge from LLMs with mechanistic interpretability](https://mlsanity.com/paper/2505.14352/) (2025)
- [How Teachers Can Use Large Language Models and Bloom's Taxonomy to Create Educational Quizzes](https://mlsanity.com/paper/2401.05914/) (2024)
- [EduQG: A Multi-format Multiple Choice Dataset for the Educational Domain](https://mlsanity.com/paper/2210.06104/) (2022)
- [Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles](https://mlsanity.com/paper/2406.12644/) (2024)
- [Mechanistic Interpretability with SAEs: Probing Religion, Violence, and Geography in Large Language Models](https://mlsanity.com/paper/2509.17665/) (2025)
- [Automated Analysis of Learning Outcomes and Exam Questions Based on Bloom's Taxonomy](https://mlsanity.com/paper/2511.10903/) (2025)
- [BloomWise: Enhancing Problem-Solving capabilities of Large Language Models using Bloom's-Taxonomy-Inspired Prompts](https://mlsanity.com/paper/2410.04094/) (2024)
- [THiNK: Can Large Language Models Think-aloud?](https://mlsanity.com/paper/2505.20184/) (2025)
- [Task complexity shapes internal representations and robustness in neural networks](https://mlsanity.com/paper/2508.05463/) (2025)
- [Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability](https://mlsanity.com/paper/2510.12229/) (2025)
- [Enhanced Bloom's Educational Taxonomy for Fostering Information Literacy in the Era of Large Language Models](https://mlsanity.com/paper/2503.19434/) (2025)
- [Beyond Tokens in Language Models: Interpreting Activations through Text Genre Chunks](https://mlsanity.com/paper/2511.16540/) (2025)

## Built on by (most cited first, 2 of 2)

- [UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering](https://mlsanity.com/paper/2605.30076/) (2026)
- [From Execution to Education: A Bloom-Aligned Framework for Measuring Educational Control in LLMs](https://mlsanity.com/paper/2607.08009/) (2026)

## Abstract (arXiv)

The black-box nature of Large Language Models necessitates novel evaluation frameworks that transcend surface-level performance metrics. This study investigates the internal neural representations of cognitive complexity using Bloom's Taxonomy as a hierarchical lens. By analyzing high-dimensional activation vectors from different LLMs, we probe whether different cognitive levels, ranging from basic recall (Remember) to abstract synthesis (Create), are linearly separable within the model's residual streams. Our results demonstrate that linear classifiers achieve approximately 95% mean accuracy across all Bloom levels, providing strong evidence that cognitive level is encoded in a linearly accessible subspace of the model's representations. These findings provide evidence that the model resolves the cognitive difficulty of a prompt early in the forward pass, with representations becoming increasingly separable across layers.