© 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. 28556
    Prev
    Next
    INDEX
    Explanations

    diagnosis or suspect

    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
    ç»Ŀ对çļĦ
    -0.08
    éĶĻ
    -0.07
    Enumerable
    -0.07
    .ud
    -0.07
    家ä¹IJ
    -0.07
    WithContext
    -0.07
    лд
    -0.07
    ëĵłì§Ģ
    -0.07
    _Top
    -0.07
    unte
    -0.07
    POSITIVE LOGITS
    çĸijä¼¼
    0.14
    ä¼¼ä¹İ
    0.14
    ä¼¼ä¹İä¹Ł
    0.13
    ä¼¼ä¹İæĺ¯
    0.13
    æľīåı¯èĥ½æĺ¯
    0.12
     seems
    0.12
    好åĥı
    0.12
    ä¼¼ä¹İåľ¨
    0.12
     suspected
    0.11
     seemed
    0.11
    Activations Density 0.197%

    No Known Activations