© 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. 44805
    Prev
    Next
    INDEX
    Explanations

    blanks to be filled

    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
    羣æľī
    -0.08
    nid
    -0.08
    æ¯ķç«Łæĺ¯
    -0.08
    æ¯ķç«Ł
    -0.08
    culares
    -0.08
    roller
    -0.07
    åĩĮéľĦ
    -0.07
    è··
    -0.07
    stad
    -0.07
    нови
    -0.07
    POSITIVE LOGITS
     Pompeo
    0.07
     punctuation
    0.06
    å¡«åħ¥
    0.06
    å°ıéĥ¨åĪĨ
    0.06
    è¡Ķ
    0.06
    æѤè¡Į
    0.06
    apus
    0.06
    .cgi
    0.06
    åįķå±Ĥ
    0.06
    åį°
    0.06
    Activations Density 0.010%

    No Known Activations