© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20459
    Prev
    Next
    INDEX
    Explanations

    nationalities and sports

    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
    çİ¯å²Ľ
    -0.06
     либо
    -0.06
     Connor
    -0.06
     Parker
    -0.06
    é¥Ńç¢Ĺ
    -0.06
    å°ıæīĭ
    -0.06
    igr
    -0.06
    ×IJ×Ļ
    -0.06
    æ³ķåĻ¨
    -0.06
    reo
    -0.06
    POSITIVE LOGITS
    łĢ
    0.07
    åľ¨åį³
    0.07
    ä¸Ģç±»
    0.07
     Uncategorized
    0.07
    è¯¥ä½ľèĢħ
    0.07
    iches
    0.06
    Behind
    0.06
    _util
    0.06
    ä½łåı¯èĥ½ä¼ļ
    0.06
     definitions
    0.06
    Activations Density 0.043%

    No Known Activations