© 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. 6429
    Prev
    Next
    INDEX
    Explanations

    government authorities or justice departments

    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
    è¡Įä¸ļä¸Ń
    -0.11
    ç¼£
    -0.10
    ocator
    -0.09
    lobby
    -0.09
    .jms
    -0.09
    .ReadAll
    -0.09
    æ·±åĬłå·¥
    -0.09
    广大群ä¼Ĺ
    -0.09
    forums
    -0.09
    éĻ¢éķ¿
    -0.09
    POSITIVE LOGITS
    ä¸ĭæĿ¥
    0.09
    ä¸Ģå¹ķ
    0.09
    çĬĬ
    0.08
    ä¸Ģ个å¤ļæľĪ
    0.08
    éªĤ
    0.08
    åŁİå¸Ĥ建设
    0.08
    并ä¸įå¤ļ
    0.08
    ä¸Ģçķª
    0.08
    ipes
    0.08
    åĽłä¸ºä»ĸ们
    0.08
    Activations Density 0.085%

    No Known Activations