© 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. 58679
    Prev
    Next
    INDEX
    Explanations

    student union representatives

    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
     pros
    -0.09
    idot
    -0.09
    åŃIJåŃĻ
    -0.08
    å°ijåIJĥ
    -0.08
    asons
    -0.08
    è°³
    -0.08
    纺
    -0.08
    /to
    -0.08
    ç¥ĵ
    -0.08
     Agency
    -0.08
    POSITIVE LOGITS
    管å§Ķä¼ļ
    0.11
    代表
    0.11
    æĪIJç«ĭ
    0.11
    代表大ä¼ļ
    0.10
    represent
    0.10
    meet
    0.10
    lice
    0.09
     committees
    0.09
    èĩªæ²»
    0.09
    -elected
    0.09
    Activations Density 0.060%

    No Known Activations