# From Observation to Intervention: A Causal Audit of Expert Importance in Mixture-of-Experts Models

arXiv: https://arxiv.org/abs/2606.10703 · HTML: https://mlsanity.com/paper/2606.10703/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Expert routing strategies, one of 12 directions in Mixture-of-experts.
- Builds on 10 of its 11 references that are in the map.
- First posted on arXiv 9 Jun 2026.

## Placed in

- Mixture-of-experts / [Expert routing strategies](https://mlsanity.com/moe/expert-routing-strategies/)

## Builds on (most cited first, 10 of 10)

- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [OLMoE: Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2409.02060/) (2024)
- [Task-Specific Expert Pruning for Sparse Mixture-of-Experts](https://mlsanity.com/paper/2206.00277/) (2022)
- [MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router](https://mlsanity.com/paper/2410.12013/) (2024)
- [SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Experts](https://mlsanity.com/paper/2404.05089/) (2024)
- [Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and Observations](https://mlsanity.com/paper/2504.05586/) (2025)
- [Causality is Key for Interpretability Claims to Generalise](https://mlsanity.com/paper/2602.16698/) (2026)

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

- [Detecting a Route Flip Is Easier Than Knowing Whether to Fix It: Causal Route-Mediated Damage in Quantized Mixture-of-Experts](https://mlsanity.com/paper/2608.11212/) (2026)
- [How Modular Is a Frontier Mixture-of-Experts? A Pre-registered Causal Test in Which Apparent Expert Modularity Mostly Dissolves](https://mlsanity.com/paper/2606.25092/) (2026)

## Abstract (arXiv)

Interpretability methods routinely use population-level summary statistics over observed model behaviour to license claims about the effects of targeted interventions on specific computations; in Pearl's terms, they treat rung-1 associational evidence as if it supported rung-2 interventional conclusions, a move whose validity is rarely tested. We examine one concrete instance: the use of routing statistics in Mixture-of-Experts (MoE) pruning, where utilization rates, activation norms, and routing weight distributions are treated as predictors of which experts can be removed without functional cost. A token-level interventional audit across three high-redundancy MoE architectures (OLMoE-1B-7B-0924, Qwen1.5-MoE-A2.7B, DeepSeek-V2-Lite) finds no observational metric predicts causal expert importance in any model: across all 60 metric-layer combinations effect sizes stay below Cohen's d = 0.23, and no metric is reliably positive under our corrected, dual-test criterion. A per-token routing weight control, run with identical n, rules out insufficient power, recovering a signal whose CI excludes zero at OLMoE's final MoE layer (d = +0.231, 95% CI [+0.09, +0.37], p = 0.0013). Existing pruning methods succeed in this regime not by identifying dispensable experts but because early-layer redundancy renders most selection criteria interchangeable. Our results provide an explicit counterexample to the common inferential step from population-level observational summaries to token-level interventional claims about expert importance, and illustrate how interventional audits can calibrate the evidential standards for interpretability claims.