© 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. 4519
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions}

    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
    OKEN
    -0.08
    èĢ³çĽ®
    -0.08
    ROTO
    -0.07
    kori
    -0.07
    èĶĶ
    -0.07
    å¾·åŁº
    -0.07
    burgh
    -0.07
    äºĨä¸ĢèĤ¡
    -0.07
    HING
    -0.07
    åĮºå§Ķ
    -0.07
    POSITIVE LOGITS
    oš
    0.07
    ugh
    0.07
     Cum
    0.07
    ç«¥
    0.07
    elf
    0.07
     Eins
    0.06
    cum
    0.06
    aps
    0.06
    esp
    0.06
    æĿ¥çļĦæŶåĢĻ
    0.06
    Activations Density 0.003%

    No Known Activations