© 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. 15727
    Prev
    Next
    INDEX
    Explanations

    Spider-Man, Hip Hop, dictionary, name, way, HH:mm:ss

    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
    æĺİçĻ½äºĨ
    -0.07
    åĨ³
    -0.06
     dott
    -0.06
    å¾Īé«ĺåħ´
    -0.06
    ادÙĩ
    -0.06
    orio
    -0.06
    uzu
    -0.06
    פת
    -0.06
    omba
    -0.06
    iedy
    -0.06
    POSITIVE LOGITS
    0.12
    à°³
    0.07
    .").
    0.06
    ÃīN
    0.06
    Âł
    0.06
    çļĦæŃ»
    0.06
    @include
    0.06
    urna
    0.06
    ;amp
    0.06
     Moc
    0.06
    Activations Density 0.856%

    No Known Activations