© 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. 52054
    Prev
    Next
    INDEX
    Explanations

    numbers and code delimiters

    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
    ++.
    -0.07
    >'.
    -0.07
     ?.
    -0.07
    **ãĢĤ
    -0.07
     '?
    -0.06
    >).
    -0.06
     );
    -0.06
    >;
    -0.06
    代çłģå¦Ĥä¸ĭ
    -0.06
    POSITIVE LOGITS
    ï¼īãĢį
    0.08
    ä»ĬæľĿ
    0.07
    ä¸ĭåIJĮ
    0.07
    mares
    0.07
    æĢ¥æĢ¥
    0.07
    ogan
    0.07
    ï¼īãĥ»
    0.07
    åħ´éļĨ
    0.07
     }}">{{
    0.07
    ario
    0.07
    Activations Density 0.349%

    No Known Activations