© 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. 40704
    Prev
    Next
    INDEX
    Explanations

    formula for average power

    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
    åįģåħ«ç«ł
    -0.08
    ört
    -0.08
    örder
    -0.08
    wan
    -0.08
    ainter
    -0.07
    åľ¨èģĮ
    -0.07
    ModuleName
    -0.07
    Logged
    -0.07
    温差
    -0.07
    ết
    -0.07
    POSITIVE LOGITS
     ren
    0.08
     normalization
    0.07
    æłĩåĩĨè¦ģæ±Ĥ
    0.07
    Normalization
    0.07
     bob
    0.06
     properly
    0.06
    ottie
    0.06
     ensuring
    0.06
    ç¡®ä¿Ŀ
    0.06
    æ¼Ĥæ³Ĭ
    0.06
    Activations Density 0.003%

    No Known Activations