© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20357
    Prev
    Next
    INDEX
    Explanations

    string type declarations

    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
    å®Ŀå±±
    -0.07
    ime
    -0.07
    è¿ĶåĽŀ顶éĥ¨
    -0.07
    apo
    -0.06
     Bakan
    -0.06
    anen
    -0.06
    财产ä¿ĿéĻ©èĤ¡ä»½æľīéĻIJåħ¬åı¸
    -0.06
    names
    -0.06
    ce
    -0.06
    alarm
    -0.06
    POSITIVE LOGITS
    äºĶä¸Ģ
    0.08
    ãģĤãģŁ
    0.07
     ìĹ
    0.07
    æĸĩæķĻ
    0.07
    è¯¥ä½ľèĢħ
    0.07
    .toolbox
    0.07
    _Syntax
    0.07
    ROL
    0.07
    æŃ£ç»ı
    0.07
    .Win
    0.07
    Activations Density 0.001%

    No Known Activations