© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52187
    Prev
    Next
    INDEX
    Explanations

    academic or scientific contexts

    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
    Negative Logits
    ',"
    -0.08
    ',//
    -0.08
    ä¸Ģæĺ¯
    -0.07
    );}
    -0.07
     ضرب
    -0.07
    ');//
    -0.07
    <|box_end|>
    -0.07
    ÙİÙĩ
    -0.07
    >>,
    -0.07
     âĸ·
    -0.07
    POSITIVE LOGITS
    æīĢæľīè¿ĻäºĽ
    0.08
     ↵↵
    0.07
    è¿Ļæł·ä¸ĢæĿ¥
    0.07
     bref
    0.07
    æīĢ以说
    0.07
    —all
    0.07
    impa
    0.06
     Therefore
    0.06
     ëĶ°ëĿ¼ìĦľ
    0.06
     Thus
    0.06
    Activations Density 0.190%

    No Known Activations