© 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. 41406
    Prev
    Next
    INDEX
    Explanations

    json structure keys

    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
    ulty
    -0.07
    /utility
    -0.07
    lish
    -0.07
    ifdef
    -0.07
    γκ
    -0.07
    /xhtml
    -0.06
    æk
    -0.06
     Hatch
    -0.06
    	Copyright
    -0.06
    éĺ
    -0.06
    POSITIVE LOGITS
     {"
    0.07
    {"
    0.07
    .newBuilder
    0.07
    obil
    0.07
    大大çļĦ
    0.07
    å¡ĺ
    0.07
    trup
    0.07
    kep
    0.06
     Cause
    0.06
    ATEST
    0.06
    Activations Density 0.383%

    No Known Activations