© 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. 61978
    Prev
    Next
    INDEX
    Explanations

    file paths like /master or #ifndef

    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
    Yii
    -0.07
    wnd
    -0.07
    üst
    -0.07
    æĺ¯åı¯ä»¥
    -0.07
     ëĿĦ
    -0.06
    ysh
    -0.06
    .borderColor
    -0.06
    /year
    -0.06
    ä½İ级
    -0.06
    opter
    -0.06
    POSITIVE LOGITS
    klin
    0.07
    ¤íģ
    0.07
     modules
    0.07
    anke
    0.07
    edu
    0.06
    _TARGET
    0.06
    çħ¦
    0.06
    ÙİÙijÙħ
    0.06
    澤
    0.06
    encial
    0.06
    Activations Density 0.101%

    No Known Activations