© 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. 56044
    Prev
    Next
    INDEX
    Explanations

    ratio, mass, weight, amounts

    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
    Õ¿
    -0.07
    непÑĢо
    -0.07
    ierte
    -0.07
    èķ
    -0.07
    ONI
    -0.06
    ilah
    -0.06
    re
    -0.06
    产åĵģä»·æł¼
    -0.06
    åĴĮåIJİ
    -0.06
    urunkan
    -0.06
    POSITIVE LOGITS
    ä¼ļåIJĮ
    0.08
    ArrayOf
    0.08
    licity
    0.07
    prite
    0.07
    gai
    0.07
    Õ¡Öģ
    0.07
    婧
    0.07
    èĶ»
    0.07
    RARY
    0.07
    agre
    0.07
    Activations Density 0.001%

    No Known Activations