© 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. 21361
    Prev
    Next
    INDEX
    Explanations

    .COMP, SQL, Set, Bluetooth, Error, CM

    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
    aje
    -0.07
     tine
    -0.06
     Feinstein
    -0.06
    è¡Ģä¸Ŀ
    -0.06
    uations
    -0.06
    umat
    -0.06
    æĹł
    -0.06
    ancybox
    -0.06
    jack
    -0.06
    conom
    -0.06
    POSITIVE LOGITS
    .fromCharCode
    0.09
    .sharedInstance
    0.08
    æĪIJç«ĭ以æĿ¥
    0.08
    ones
    0.07
    æ¢
    0.07
    tha
    0.07
    تا
    0.07
    éĵĿä¸ļ
    0.07
    rück
    0.07
    RESH
    0.06
    Activations Density 0.226%

    No Known Activations