© 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. 58676
    Prev
    Next
    INDEX
    Explanations

    sports, yoga, and dance

    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
     histories
    -0.08
    ç¼Ħ
    -0.08
    åĹĵåŃIJ
    -0.07
    åħ¼èģĮ
    -0.07
    ä¸ļåĬ¡ç´łè´¨
    -0.07
    ä½ľåĿĬ
    -0.07
    agi
    -0.07
    éģŃéģĩ
    -0.07
    jek
    -0.07
    lyph
    -0.07
    POSITIVE LOGITS
     upright
    0.07
     yoga
    0.07
    ç«Ļç«ĭ
    0.07
     exaggerated
    0.07
     comfortably
    0.07
     Kushner
    0.07
    缴ç«ĭ
    0.07
    ä¼¸çĽ´
    0.07
    æģ©æĸ¯
    0.07
     Yoga
    0.07
    Activations Density 0.020%

    No Known Activations