© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37604
    Prev
    Next
    INDEX
    Explanations

    ThinkPHP copyright

    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
    Negative Logits
    /or
    -0.10
    ê»ĺ
    -0.09
    สà¹Į
    -0.09
    à¸ķà¹Į
    -0.09
    weiler
    -0.08
    etic
    -0.08
    waran
    -0.08
    utzt
    -0.08
    ãģĬãĤĬãģ¾ãģĻ
    -0.08
    vironment
    -0.07
    POSITIVE LOGITS
    gether
    0.09
    ë§ĪìŀIJ
    0.09
    ting
    0.08
    ÑģÑĮ
    0.08
    ï¸ı
    0.08
    omÄĽ
    0.08
    anders
    0.07
    raries
    0.07
    人æĿ¥è¯´
    0.07
    ity
    0.07
    Activations Density 0.067%

    No Known Activations