© 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. 3457
    Prev
    Next
    INDEX
    Explanations

    program startup or main function

    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
     rowspan
    -0.07
    /rfc
    -0.06
    ardy
    -0.06
     sze
    -0.06
     Carn
    -0.06
    uples
    -0.06
    éļĶ
    -0.06
     objectId
    -0.06
    _operand
    -0.06
    åı¯æĢľ
    -0.06
    POSITIVE LOGITS
     startup
    0.10
     Main
    0.10
    setup
    0.10
     main
    0.10
    .setup
    0.10
    .Main
    0.09
     setup
    0.09
    .main
    0.09
    åķŁåĭķ
    0.09
    startup
    0.09
    Activations Density 1.072%

    No Known Activations