© 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. 44614
    Prev
    Next
    INDEX
    Explanations

    sqrt followed by (

    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
    ä¸įè¯Ĩ
    -0.08
    chk
    -0.08
    ajak
    -0.08
    chy
    -0.07
    miss
    -0.07
    eli
    -0.07
    UDO
    -0.07
    è¡Į为åĴĮ
    -0.07
    ials
    -0.07
     STDERR
    -0.07
    POSITIVE LOGITS
    infinity
    0.06
    æ¸Ĺ
    0.06
    амеÑĤ
    0.06
    ï¸ı
    0.06
    _REFRESH
    0.06
    istically
    0.06
    ä¸īæĺ¯
    0.06
     la
    0.06
    ìĤ¼
    0.06
    0.06
    Activations Density 0.013%

    No Known Activations