© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29672
    Prev
    Next
    INDEX
    Explanations

    code punctuation closing statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ëıĻìĿ´
    -0.07
    è¡Įæĥħ
    -0.07
     Lawson
    -0.06
    æij
    -0.06
    gun
    -0.06
    æĿ¾
    -0.06
    øk
    -0.06
    edar
    -0.06
    à´ķàµįà´ķ
    -0.06
    纬
    -0.06
    POSITIVE LOGITS
    اÛĮØ´
    0.07
    ãĤĪãģĹ
    0.07
    åİŁåĽłå°±æĺ¯
    0.07
     поÑįÑĤомÑĥ
    0.07
    ÙİÙĨ
    0.07
     joten
    0.07
    arno
    0.06
    iedo
    0.06
    ãģ¨ãģĦãģĨãģĵãģ¨ãģ¯
    0.06
    ç¼®
    0.06
    Activations Density 0.016%

    No Known Activations