© 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. 31284
    Prev
    Next
    INDEX
    Explanations

    J. League, 8 Out of 10 Cats, Swords & Soldiers

    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
    Å¡tÄĽ
    -0.07
     Leslie
    -0.07
    rze
    -0.06
    ÑĢка
    -0.06
    å¼ı设计
    -0.06
    chalk
    -0.06
    unen
    -0.06
    üb
    -0.06
    chor
    -0.06
    rš
    -0.06
    POSITIVE LOGITS
    àºĩ
    0.08
    Ĥ¹
    0.08
    æĪ´ç»´æĸ¯
    0.07
    jang
    0.07
    iform
    0.07
    åĭī
    0.07
    -dat
    0.07
    bsp
    0.07
    æĸĩåѦå¥ĸ
    0.07
    avel
    0.07
    Activations Density 0.301%

    No Known Activations