© 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. 43392
    Prev
    Next
    INDEX
    Explanations

    flowable, dto, wrapper, implementation, import

    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
    ApplicationBuilder
    -0.08
    .toInt
    -0.07
     MyApp
    -0.07
    loe
    -0.07
    /welcome
    -0.07
    èĩªæĭĶ
    -0.07
    бÑĢе
    -0.07
    æľ¬ç«ĻåĨħ容
    -0.07
    killer
    -0.07
    uluk
    -0.07
    POSITIVE LOGITS
    wrapper
    0.09
    Wrapper
    0.08
    _wrapper
    0.08
    .wrapper
    0.08
    è¨Ĺ
    0.08
     Wrapper
    0.08
     underlying
    0.07
    åİŁåŀĭ
    0.07
     native
    0.07
    ä¼łæĿ¥çļĦ
    0.07
    Activations Density 0.755%

    No Known Activations