© 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. 62369
    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
     confin
    -0.07
     Tee
    -0.07
    erve
    -0.06
     기ìļ¸
    -0.06
    çľ¼çĿģ
    -0.06
    /misc
    -0.06
    HOST
    -0.06
     EQUAL
    -0.06
    abad
    -0.06
     GMT
    -0.06
    POSITIVE LOGITS
    ä¸įå·²
    0.07
    леÑĤов
    0.07
    æĬĢèĥ½äººæīį
    0.07
    opper
    0.07
    stash
    0.07
    天éĻħ
    0.07
    gow
    0.07
    _EXPR
    0.07
    عÙĬØ©
    0.07
    cker
    0.06
    Activations Density 0.000%

    No Known Activations