© 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. 27988
    Prev
    Next
    INDEX
    Explanations

    underwent, function, platform, annually

    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
    woff
    -0.07
     Borr
    -0.07
    kör
    -0.07
    engesch
    -0.07
    ä¸İ人
    -0.06
    à¸ŀร
    -0.06
    ORD
    -0.06
    ç»ĵ
    -0.06
    .fixed
    -0.06
    ä¸įæĸŃæİ¨è¿Ľ
    -0.06
    POSITIVE LOGITS
    æİĸ
    0.09
    袴
    0.09
    éĩĮåħĭ
    0.07
    à¸ĵà¹Į
    0.07
    ouser
    0.07
    chá
    0.07
    _FRIEND
    0.07
    isional
    0.07
    ëĪĦ
    0.07
    æ°ijéĸĵ
    0.07
    Activations Density 0.002%

    No Known Activations