© 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. 50233
    Prev
    Next
    INDEX
    Explanations

    code parentheses and statements

    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
    iot
    -0.07
     Omn
    -0.06
    ']}
    -0.06
    >_
    -0.06
    menn
    -0.06
    æľīæĿ¡
    -0.06
    ä»¥æĽ´
    -0.06
     rata
    -0.06
    èĦ¸çļĦ
    -0.06
    ä¹ĭ忧
    -0.06
    POSITIVE LOGITS
    ricks
    0.08
    褶
    0.08
    .Accessible
    0.08
    itten
    0.08
    æ»´æ°´
    0.08
    ensee
    0.08
    skyl
    0.07
    è¾¾åħĭ
    0.07
    .mas
    0.07
    deps
    0.07
    Activations Density 0.142%

    No Known Activations