© 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. 597
    Prev
    Next
    INDEX
    Explanations

    kits and packages

    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
    anim
    -0.07
    éķ¿è¡¥çŁŃ
    -0.07
    æĽ´å¤ļ精彩
    -0.07
    .addChild
    -0.07
    ানà§įত
    -0.07
    _TYP
    -0.07
     sometime
    -0.07
    åĸľæ°Ķ
    -0.07
    quist
    -0.07
    dain
    -0.07
    POSITIVE LOGITS
     usable
    0.13
     guidance
    0.12
     sẵn
    0.12
    åı¯ä¾Ľ
    0.11
     ready
    0.11
     guides
    0.10
    éħįå¥Ĺ
    0.10
     пÑĢедоÑģÑĤавлÑı
    0.10
    è¿ĺæıIJä¾Ľ
    0.10
    ä¾Ľå¤§å®¶
    0.10
    Activations Density 0.500%

    No Known Activations