© 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. 26084
    Prev
    Next
    INDEX
    Explanations

    mathematical operators or computer code

    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
    idou
    -0.08
    åĩºåħ¥
    -0.08
    à¹ĩà¸Ķ
    -0.07
     تÙĤرÙĬب
    -0.07
    /MIT
    -0.07
    zach
    -0.07
    /request
    -0.07
    cia
    -0.07
    iza
    -0.07
    _exc
    -0.07
    POSITIVE LOGITS
    mute
    0.07
    berman
    0.07
    åķıãĤıãģļ
    0.06
    ÛĮ
    0.06
    лам
    0.06
    è¿ĩå±±
    0.06
    oszt
    0.06
    éĩijèī²çļĦ
    0.06
    åĵ¥çļĦ
    0.06
     mest
    0.06
    Activations Density 0.002%

    No Known Activations