© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6060
    Prev
    Next
    INDEX
    Explanations

    python code or names like Bobby Brown

    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
    Negative Logits
    ssel
    -0.08
    ç«¿
    -0.08
    è¤Ĵ
    -0.08
     Seventh
    -0.08
    s
    -0.08
    7
    -0.08
    icates
    -0.07
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.07
     mell
    -0.07
     Det
    -0.07
    POSITIVE LOGITS
    ä¼ĹæīĢ
    0.10
    鲨
    0.10
    è¾ĥå¿«
    0.09
    大象
    0.09
    ifold
    0.09
    åķ¡
    0.09
    levator
    0.09
    erness
    0.09
    干线
    0.09
    åŃ
    0.09
    Activations Density 0.406%

    No Known Activations