© 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. 59869
    Prev
    Next
    INDEX
    Explanations

    time, status, or tasks

    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
    éĺħè¯»æľ¬æĸĩåīį
    -0.07
    à§įরà§ĩ
    -0.07
    iasco
    -0.07
    æ··
    -0.07
    åĪ«æľī
    -0.07
    licative
    -0.06
    åħį费订éĺħ
    -0.06
    atica
    -0.06
    æĸ°ä¹¦æݨèįIJ
    -0.06
    utow
    -0.06
    POSITIVE LOGITS
    à®ļà¯įà®ļ
    0.07
     Kini
    0.07
     berb
    0.07
    ç¢į
    0.07
    ç¤Ļ
    0.07
     saz
    0.06
    æĢĿèĢĥåĴĮ
    0.06
    èIJ½èIJ½
    0.06
    è¿Ļä»½å·¥ä½ľ
    0.06
    æĴ
    0.06
    Activations Density 0.001%

    No Known Activations