© 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. 15642
    Prev
    Next
    INDEX
    Explanations

    relative imports of code modules

    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
    izont
    -0.07
    æĿ¡
    -0.06
    uet
    -0.06
    iest
    -0.06
    rix
    -0.06
    à¹ģหà¹Īà¸ĩ
    -0.06
    ÑĢока
    -0.06
    amil
    -0.06
     derr
    -0.06
    inkt
    -0.06
    POSITIVE LOGITS
    ../../../
    0.08
    ä½ķåİ»ä½ķ
    0.08
    zelf
    0.07
    缮å½ķä¸Ģè§Ī
    0.07
     Lowell
    0.07
    ä¿©
    0.07
    .Dispatch
    0.07
    ÙĦÙĪÙĦ
    0.07
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.07
    ownik
    0.07
    Activations Density 0.286%

    No Known Activations