© 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. 50339
    Prev
    Next
    INDEX
    Explanations

    4.365.271.385 formatted 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
    ingly
    -0.09
    enate
    -0.08
    irsi
    -0.08
    rotch
    -0.08
    /cgi
    -0.08
    å¿¿
    -0.08
    yam
    -0.08
    à¹Ģà¸Ĭà¹Īà¸Ļà¸Ļัà¹īà¸Ļ
    -0.07
    lod
    -0.07
    .Ticks
    -0.07
    POSITIVE LOGITS
     masc
    0.06
    Ïİν
    0.06
    大è§Ĥ
    0.06
     ë²Ķ
    0.06
     evac
    0.06
     rap
    0.06
     deb
    0.06
     ÙĪاØŃ
    0.06
     fearing
    0.06
    ä¸Ģå¹´
    0.06
    Activations Density 0.003%

    No Known Activations