© 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. 59105
    Prev
    Next
    INDEX
    Explanations

    section of

    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
    ingi
    -0.08
    [Math
    -0.08
    ool
    -0.08
    严äºİ
    -0.07
    ools
    -0.07
    leans
    -0.07
    åĸľæĢĴåĵĢ
    -0.07
    ooled
    -0.07
    bern
    -0.07
    åŃ¦ä¹łä¸Ĭ
    -0.07
    POSITIVE LOGITS
    åĴĮ第
    0.08
    gadas
    0.07
    åı¸
    0.07
    пÑı
    0.06
    天é¾Ļ
    0.06
     plus
    0.06
    reden
    0.06
    лÑĥÑĩ
    0.06
    Ú¯ÛĮ
    0.06
    aca
    0.06
    Activations Density 0.202%

    No Known Activations