© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23021
    Prev
    Next
    INDEX
    Explanations

    geometric mean and average

    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
    /disable
    -0.08
    大æĦı
    -0.08
    endon
    -0.08
    richten
    -0.08
    igem
    -0.07
    ׼×Ķ
    -0.07
    _SOURCE
    -0.07
    agni
    -0.07
    ç»ĵæŀĦåĮĸ
    -0.07
    cket
    -0.07
    POSITIVE LOGITS
    kali
    0.08
     lùi
    0.08
     approach
    0.07
     Approach
    0.07
    ç«¿
    0.07
     formula
    0.07
    ä¼Ļä¼´
    0.07
     weighted
    0.06
    0.06
    èIJ¥éĢł
    0.06
    Activations Density 0.003%

    No Known Activations