© 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. 51247
    Prev
    Next
    INDEX
    Explanations

    tic-tac-toe

    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
    oling
    -0.07
    éĩįåĨĻ
    -0.07
    åĨĽä¸Ń
    -0.07
    èįIJ
    -0.07
    à¹Ģà¸ģลà¹īา
    -0.06
    repid
    -0.06
    æĮĿ
    -0.06
     equip
    -0.06
    æѤ类
    -0.06
    åİŁçīĪ
    -0.06
    POSITIVE LOGITS
    åĽ´æ£ĭ
    0.09
    æ£ĭ
    0.09
    zug
    0.07
    æ¸ħæĺİ
    0.07
    ç»Ħç»ĩ建设
    0.07
    ະ
    0.07
    pace
    0.07
    singleton
    0.07
    åħ±èµ¢
    0.07
    itect
    0.07
    Activations Density 0.008%

    No Known Activations