© 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. 21411
    Prev
    Next
    INDEX
    Explanations

    code comments and style indicators

    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
    建åįİ
    -0.08
    èĩ
    -0.08
    xxxxxxxx
    -0.08
    XXXXXXXX
    -0.08
    缸åħ³äº§åĵģ
    -0.07
    urb
    -0.07
    reet
    -0.07
    <html
    -0.07
    ï¼ļ<
    -0.07
    vie
    -0.07
    POSITIVE LOGITS
    antis
    0.07
    æĸĩçIJĨ
    0.06
    ablement
    0.06
    antan
    0.06
    æł¡çº§
    0.06
    plom
    0.06
    dain
    0.06
    иÑģи
    0.06
     plag
    0.06
    idou
    0.06
    Activations Density 0.005%

    No Known Activations