feat: add support for Qwen3Next shared experts

[umran666]

Adds layer.mlp.shared_expert.down_proj to the abliteration targets.

This ensures that the shared expert in Qwen3-Next MoE models (which handles a significant portion of general knowledge) is properly abliterated.

The AttributeError on self_attn reported in the issue is already mitigated by the suppress(Exception) blocks added previously to master.

[gemini-code-assist]

Code Review

This pull request updates src/heretic/model.py to attempt to add the mlp.down_proj component from a layer's shared expert, wrapping the call in an exception suppression block. There are no review comments, so I have no feedback to provide.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

[umran666]

Fixes #181