© 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. 35077
    Prev
    Next
    INDEX
    Explanations

    Russian surnames and patronymics

    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
    achim
    -0.08
    зе
    -0.07
    使çĶ¨åIJİ
    -0.07
    åijľ
    -0.07
    utsch
    -0.07
    _pw
    -0.07
    è¿Ļç§įä¸ľè¥¿
    -0.07
    èĢ¶
    -0.06
    åĬ¨ä¸įåĬ¨
    -0.06
    å½±éŁ³
    -0.06
    POSITIVE LOGITS
    éĻħ
    0.07
    ront
    0.07
    ulton
    0.06
    è´Łè´£çļĦ
    0.06
     incom
    0.06
    geb
    0.06
    æĹłæŀģ
    0.06
     thereof
    0.06
     old
    0.06
    è¾Ī
    0.06
    Activations Density 0.054%

    No Known Activations