© 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. 63500
    Prev
    Next
    INDEX
    Explanations

    Mayor, Company, Guild, Hall

    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
    大èĩ´
    -0.10
    vio
    -0.10
    ç»Ģ
    -0.09
    åĪĨå±Ģ
    -0.08
    éĢĨ
    -0.08
    _UNLOCK
    -0.08
     ná»iji
    -0.08
    dzi
    -0.08
    mites
    -0.08
     Pussy
    -0.08
    POSITIVE LOGITS
     guild
    0.09
    åŃĹåı·
    0.09
    åķĨæĪ·
    0.09
    èµ°åĩºæĿ¥
    0.09
    å¤ĸåĩº
    0.08
    Å©
    0.08
    丢
    0.08
    èĬĿ麻
    0.08
    åķĨçĶ¨
    0.08
     pud
    0.08
    Activations Density 0.170%

    No Known Activations