© 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. 17362
    Prev
    Next
    INDEX
    Explanations

    family members and help

    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
    主æµģ
    -0.10
     mommy
    -0.09
    ä¼Ļä¼´
    -0.09
    ä¸į对
    -0.09
    åħ¬çĽĬ
    -0.08
    åºĵéĩĮ
    -0.08
     Partner
    -0.08
    ç¾İ人
    -0.08
    prüf
    -0.08
    _RATE
    -0.08
    POSITIVE LOGITS
    缸èģļ
    0.11
    第ä¸ī代
    0.10
    ä¸ĭä¸Ģ代
    0.10
     grandchildren
    0.10
    éķ¿è¾Ī
    0.09
    çľĭæľĽ
    0.09
    é¦Ī
    0.09
    åŃĻåŃIJ
    0.09
    è¾Ī
    0.09
     grand
    0.08
    Activations Density 0.072%

    No Known Activations