© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35125
    Prev
    Next
    INDEX
    Explanations

    cytochrome P450

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĽijçĿ£ç®¡çIJĨ
    -0.10
    çıĪ
    -0.09
    åijľ
    -0.09
    ç¡İ
    -0.09
    ermen
    -0.09
    recht
    -0.09
    erness
    -0.09
     bids
    -0.09
    INDER
    -0.09
    hunt
    -0.09
    POSITIVE LOGITS
    æĹłå¿§
    0.09
    åIJĦéĥ¨éŨ
    0.08
    å¾Ħ
    0.08
    çľ¼éķľ
    0.08
    平淡
    0.08
    çŃ¾ç½²
    0.08
    lass
    0.08
    å®ŀäºĭæ±Ĥæĺ¯
    0.08
    ç´Ģ
    0.08
    å°º
    0.08
    Activations Density 0.232%

    No Known Activations