© 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. 12783
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or Field

    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
    ÐijÐł
    -0.07
    usty
    -0.07
    ieber
    -0.07
     Gis
    -0.07
    orny
    -0.07
    yani
    -0.07
    geber
    -0.07
    ople
    -0.07
    æ»¡åľ°
    -0.07
    ris
    -0.07
    POSITIVE LOGITS
    ä¸įå¿ĺ
    0.08
    ä¸į容
    0.08
    åĪĨæŀIJåıĬ
    0.07
    åľ¨ä¼ļä¸Ĭ
    0.07
    uv
    0.07
    åIJĪæĪIJ
    0.06
    åĥļ
    0.06
    èĥĮåIJİ
    0.06
    еÑģа
    0.06
    åŃ¦å£«åѦä½į
    0.06
    Activations Density 0.001%

    No Known Activations