© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17316
    Prev
    Next
    INDEX
    Explanations

    code constructs ending in ); or ;

    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
     ãĢģ
    -0.09
    ()},
    -0.08
    /
    -0.08
    ãĢģ
    -0.08
    $',
    -0.07
    []>(
    -0.07
    çŃīè¿Ľè¡Į
    -0.07
    **”
    -0.07
    "](
    -0.07
    çŃīéĥ½æĺ¯
    -0.07
    POSITIVE LOGITS
    arda
    0.08
    owell
    0.08
    toral
    0.07
    osas
    0.07
    å±ķè§Īå±ķ示
    0.07
    ئÙĩ
    0.07
    ä¸ĭ载次æķ°
    0.07
    ofile
    0.07
    UER
    0.07
    ħ§
    0.07
    Activations Density 0.130%

    No Known Activations