© 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. 806
    Prev
    Next
    INDEX
    Explanations

    smart usage tips

    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
    åIJĮè¡Į
    -0.07
    ersen
    -0.07
    _COMPLEX
    -0.07
    èĺij
    -0.07
    zana
    -0.07
    -plugins
    -0.07
    á»Ļn
    -0.07
    AGR
    -0.07
    .cleaned
    -0.06
    ä¸Ńæµ·
    -0.06
    POSITIVE LOGITS
    elic
    0.08
    身为
    0.08
    æ¯ı天éĥ½è¦ģ
    0.07
    稳
    0.07
    æĪIJçĨŁçļĦ
    0.07
    ç¨³åĽº
    0.07
    åĽºå®ļ
    0.07
     бла
    0.06
    å¹³æĹ¥éĩĮ
    0.06
     stead
    0.06
    Activations Density 0.169%

    No Known Activations