© 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. 7071
    Prev
    Next
    INDEX
    Explanations

    specialized text examples

    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
     ÐŁÐ¾Ð¿ÑĢо
    -0.08
     Сооб
    -0.07
    æĹ¢å®ļ
    -0.07
     Denn
    -0.07
     Consort
    -0.07
     semifinal
    -0.07
    å¤įåĪ¶éĵ¾æİ¥
    -0.07
    åĽ
    -0.07
    çİī
    -0.07
     Erot
    -0.06
    POSITIVE LOGITS
    abez
    0.08
    åŃ¦ä¹łä¸İ
    0.07
    åĨħ容åıĬ
    0.07
    å°ıçŁ¥è¯Ĩ
    0.07
    讲解äºĨ
    0.07
    åĨħ容åĮħæĭ¬
    0.07
    çļĦä¸ĢçĶŁ
    0.07
    讲æİĪ
    0.07
    .ga
    0.07
     utility
    0.07
    Activations Density 0.005%

    No Known Activations