# Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition

**Type:** Papers  
**Canonical URL:** https://scholariq.org/papers/hierarchical-sparse-circuit-extraction-from-billion-parameter-language-models/

## Facts

| Field | Value |
| --- | --- |
| Author Names | Mohammed Mudassir Uddin,Alam, Shahnawaz,M. A. Aleem Pasha |
| Citations | 0 |
| DOI | 10.48550/arxiv.2601.12879 |
| Fields | Computer Science |
| Open Access | true |
| OA Status | green |
| OA URL | https://doi.org/10.48550/arxiv.2601.12879 |
| OpenAlex ID | https://openalex.org/W7125191600 |
| Type | preprint |
| Year | 2026 |

## Paper authors

- [M. A. Aleem Pasha](https://scholariq.org/researchers/m-a-aleem-pasha/)

## Paper journal

- [arXiv (Cornell University)](https://scholariq.org/journals/arxiv-cornell-university/)

## Paper primary topic

- [Advanced Graph Neural Networks](https://scholariq.org/topics/advanced-graph-neural-networks/)

## Paper topics

- [Advanced Graph Neural Networks](https://scholariq.org/topics/advanced-graph-neural-networks/)
- [Explainable Artificial Intelligence (XAI)](https://scholariq.org/topics/explainable-artificial-intelligence-xai/)
- [Adversarial Robustness in Machine Learning](https://scholariq.org/topics/adversarial-robustness-in-machine-learning/)

---
Source: ScholarIQ — public research metadata, principally OpenAlex. See https://scholariq.org/sources/ for provenance and https://scholariq.org/methodology/ for what these figures mean.