© 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. 2077
    Prev
    Next
    INDEX
    Explanations

    I'm / I have

    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
     dott
    -0.08
    sgi
    -0.08
    _LOOK
    -0.08
    æ¼ĵ
    -0.07
    cribir
    -0.07
    è¿Ļ次活åĬ¨
    -0.07
    æĿİå¿Ĺ
    -0.07
    ÑĢÑijÑħ
    -0.07
    ilee
    -0.07
    koz
    -0.07
    POSITIVE LOGITS
     Pai
    0.07
    ç¿»
    0.07
    icat
    0.06
    æīĢæĮĩ
    0.06
    ARDS
    0.06
    i
    0.06
    (
    0.06
    AI
    0.06
    Ä°
    0.06
    å¯ĮåĬĽ
    0.06
    Activations Density 0.008%

    No Known Activations