© 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. 20289
    Prev
    Next
    INDEX
    Explanations

    Mexican Hat, P, NAFTA, Hole, vertex

    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
    åıĪæĬĬ
    -0.07
    ORB
    -0.07
    unda
    -0.07
    ä¸ĢåĽŀäºĭ
    -0.07
    kola
    -0.07
    大æīĭ
    -0.07
    ä¼łä¸ĸ
    -0.07
    version
    -0.06
    åı¯ä»¥å°Ĩ
    -0.06
    éĸĵãģ¯
    -0.06
    POSITIVE LOGITS
    ť
    0.08
    -hop
    0.07
    edes
    0.07
     giá»Ŀ
    0.07
    _tools
    0.07
     //~
    0.07
    PLIC
    0.07
     //*
    0.06
    æºIJçļĦ
    0.06
    å¼Ģå§ĭåľ¨
    0.06
    Activations Density 0.010%

    No Known Activations