How Pruning Reshapes Features: Sparse Autoencoder Analysis of Weight-Pruned Language Models

Weight pruning is a standard technique for compressing large language models, yet its effect on learned internal representations remains poorly understood. We present the first systematic study of how unstructured pruning reshapes the feature geometry of language models, using Sparse Autoencoders (SAEs) as interpretability probes. Across three model families (Gemma 3 1B, Gemma 2 2B, Llama 3.2 1B), two pruning methods (magnitude and Wanda), and six sparsity levels (0--60%), we investigate five research questions spanning seed stability, feature survival, SAE transferability, feature fragility, and causal relevance. Our most striking finding is that rare SAE features--those with low firing rates--survive pruning far better than frequent ones, with within-condition Spearman correlations of rho = -1.0 in 11 of 17 experimental conditions. This counter-intuitive result suggests that pruning acts as implicit feature selection, preferentially destroying high-frequency generic features while preserving specialized rare ones. We further show that Wanda pruning preserves feature structure up to 3.7x better than magnitude pruning, that pre-trained SAEs remain viable on Wanda-pruned models up to 50% sparsity, and that geometric feature survival does not predict causal importance--a dissociation with implications for interpretability under compression.

Functional Component Ablation Reveals Specialization Patterns in Hybrid Language Model Architectures

Hybrid language models combining attention with state space models (SSMs) or linear attention offer improved efficiency, but whether both components are genuinely utilized remains unclear. We present a functional component ablation framework applied to two sub-1B hybrid models -- Qwen3.5-0.8B (sequential: Gated DeltaNet + softmax attention) and Falcon-H1-0.5B (parallel: Mamba-2 + attention) -- with a pure Transformer control (Qwen2.5-0.5B). Through group ablations, layer-wise sweeps, positional ablations, matched random controls, and perplexity analysis across five benchmarks, we establish four findings: (1) both component types are essential and neither is bypassed; (2) the alternative component (linear attention or SSM) is the primary language modeling backbone, causing >35,000x perplexity degradation when removed versus ~82x for attention; (3) component importance follows a positional gradient, with early layers being disproportionately critical; and (4) hybrid architectures exhibit 20-119x greater resilience to random layer removal than pure Transformers, revealing built-in functional redundancy between component types. These results provide actionable guidance for hybrid model compression, architecture design, and fault-tolerant deployment.