© 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. 49663
    Prev
    Next
    INDEX
    Explanations

    numerical data following periods

    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
    äº¬ä¸ľåķĨåŁİ
    -0.08
    miny
    -0.08
    -REAL
    -0.08
    å¾·åĭĴ
    -0.08
    abouts
    -0.08
    alami
    -0.08
    ä¸įå¿«
    -0.08
     kick
    -0.08
    ç¼¥
    -0.08
    azan
    -0.08
    POSITIVE LOGITS
     combination
    0.07
    ç»ĦåIJĪ
    0.07
    ä¸ºæľŁ
    0.07
    çļĦç»ĦåIJĪ
    0.06
    æıIJ示
    0.06
    æĸ°å¥ĩ
    0.06
    oux
    0.06
    æĬ½æł·
    0.06
     Nicol
    0.06
     hormone
    0.06
    Activations Density 0.009%

    No Known Activations