© 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. 55955
    Prev
    Next
    INDEX
    Explanations

    personal or private services

    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
    ä»ģ
    -0.09
    à¸ķร
    -0.09
     Cargo
    -0.08
     place
    -0.08
     Place
    -0.08
    é¢ľ
    -0.08
    _flush
    -0.08
    emm
    -0.08
    ç»ıèIJ¥æ´»åĬ¨
    -0.08
     storing
    -0.08
    POSITIVE LOGITS
    ä¸ĵ人
    0.13
    ç§ģ人
    0.12
    ä¿Ŀå§Ĩ
    0.12
    èģĺ请
    0.11
    管家
    0.11
    åĬ©æīĭ
    0.11
    è´´å¿ĥ
    0.11
    ä¹°åįķ
    0.11
    缩å°ı
    0.10
    vip
    0.10
    Activations Density 0.092%

    No Known Activations