© 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. 49239
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Zob
    -0.07
    åįİåķĨ
    -0.07
     DeV
    -0.07
    æīĢæĮģ
    -0.06
    ä¸Ģåı¶
    -0.06
    åIJ«æ°´
    -0.06
    wort
    -0.06
    æł·
    -0.06
    ä¸Ĭæ·»
    -0.06
    åIJįæĢĿ
    -0.06
    POSITIVE LOGITS
    ruh
    0.07
    μι
    0.07
    AGR
    0.07
    isky
    0.07
    िन
    0.07
    InBackground
    0.07
    jež
    0.07
    FT
    0.07
    éĽ¯
    0.07
    .INSTANCE
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.