© 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. 4885
    Prev
    Next
    INDEX
    Explanations

    formula IF SUM

    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
    ogia
    -0.09
    uwe
    -0.08
    gau
    -0.08
    ãĥ³
    -0.08
    kini
    -0.08
    ëŀĢ
    -0.08
    ucho
    -0.08
    kot
    -0.08
    usk
    -0.08
    ué
    -0.07
    POSITIVE LOGITS
    ìľł
    0.07
    iom
    0.07
    åŃIJåĴĮ
    0.06
    交æīĢ
    0.06
    åŃIJéĩĮ
    0.06
     chÄĥng
    0.06
    inth
    0.06
    ersh
    0.06
    ixon
    0.06
    åĴĮä¸į
    0.06
    Activations Density 0.031%

    No Known Activations