© 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. 26488
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    iskon
    -0.08
     Maggi
    -0.08
    мÑĸнÑĸ
    -0.08
    ï¼įï¼į
    -0.08
    åķĨåĬ¡ä¸Ńå¿ĥ
    -0.08
    ÑĢиан
    -0.07
    åĮºåĮº
    -0.07
    ++++
    -0.07
    cias
    -0.07
     ragaz
    -0.07
    POSITIVE LOGITS
    uhan
    0.07
     or
    0.06
    umer
    0.06
    为åįķä½į
    0.06
    æŁı
    0.06
    hen
    0.06
    ç»Ŀèī²
    0.06
    acon
    0.06
    ucle
    0.06
    rah
    0.06
    Activations Density 0.007%

    No Known Activations