© 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. 57532
    Prev
    Next
    INDEX
    Explanations

    large numbers

    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
    ĻĤ
    -0.08
    à¯įப
    -0.08
    stocks
    -0.08
    alat
    -0.08
    ibert
    -0.08
    JECTED
    -0.07
    Õ¼
    -0.07
    LEEP
    -0.07
    stock
    -0.07
    ÃŃst
    -0.07
    POSITIVE LOGITS
    央
    0.06
    ackets
    0.06
     MIS
    0.06
    æīĵåĩº
    0.06
    0.06
    ä»ĸæĢ»æĺ¯
    0.06
    .fire
    0.06
     Pla
    0.06
    ç¢į
    0.06
    æ¯ĶåĪĨ
    0.05
    Activations Density 0.003%

    No Known Activations