© 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. 9232
    Prev
    Next
    INDEX
    Explanations

    now followed by punctuation

    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
    ettino
    -0.09
    zent
    -0.09
    eson
    -0.08
    joj
    -0.08
    æĸ°éĹ»ç½ij
    -0.08
    尼奥
    -0.07
    зд
    -0.07
    eness
    -0.07
    irim
    -0.07
    íĭĢ
    -0.07
    POSITIVE LOGITS
    adays
    0.09
    å¯¹åľ¨
    0.07
    æģIJ
    0.06
    æĿ¥ãģ®
    0.06
    Úº
    0.06
     ../../../
    0.06
    aminer
    0.06
    ä¸ĭæĸĩ
    0.06
     António
    0.06
     Ãģlvaro
    0.06
    Activations Density 0.012%

    No Known Activations