© 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. 55283
    Prev
    Next
    INDEX
    Explanations

    osteonecrosis, epilepsy, fatty liver

    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
    æĮ¯
    -0.07
    bell
    -0.07
    ters
    -0.06
    imper
    -0.06
    áŀ¶áŀĶáŁĭ
    -0.06
    çĹħåѦ
    -0.06
    ikan
    -0.06
    eger
    -0.06
    à¥Īन
    -0.06
    缨
    -0.06
    POSITIVE LOGITS
    -of
    0.15
    -from
    0.12
    -on
    0.11
    à¹ģหà¹Īà¸ĩ
    0.09
    æĸ¼
    0.09
     ìĺ¤ë¸Į
    0.09
    äºİ
    0.09
    -at
    0.09
    -with
    0.09
    _of
    0.09
    Activations Density 0.738%

    No Known Activations