© 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. 37711
    Prev
    Next
    INDEX
    Explanations

    . and is

    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
    ppi
    -0.08
    uldig
    -0.07
    ZA
    -0.07
    erville
    -0.07
    æ²®
    -0.06
    isso
    -0.06
    ä¾Ŀå±±
    -0.06
    æľĿå¤ķ
    -0.06
    _batches
    -0.06
    abic
    -0.06
    POSITIVE LOGITS
    ä¸įåľ¨
    0.08
    æŃ£å¥½
    0.08
    rese
    0.08
    æĺ¯åIJ¦åľ¨
    0.08
    æģ°å¥½
    0.08
    æĺ¯åIJ¦ç¬¦åIJĪ
    0.08
    ç¨
    0.08
    afe
    0.08
    _collision
    0.07
    èĤ¡
    0.07
    Activations Density 0.058%

    No Known Activations