© 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. 13442
    Prev
    Next
    INDEX
    Explanations

    catch exception

    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
    mdl
    -0.08
    UDO
    -0.07
     Filos
    -0.07
    udou
    -0.07
    ä¸Ģä¸ĭ
    -0.07
    Uvs
    -0.07
    fern
    -0.07
    .va
    -0.06
    ç»į
    -0.06
    gos
    -0.06
    POSITIVE LOGITS
    irse
    0.08
    ught
    0.07
    Caught
    0.07
    éĤ£å¼ł
    0.07
    _FAILED
    0.07
    è¯ĬæĸŃåıĬ
    0.07
    idents
    0.07
     exc
    0.07
    IFEST
    0.07
    <![
    0.06
    Activations Density 0.021%

    No Known Activations