© 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. 35002
    Prev
    Next
    INDEX
    Explanations

    invention relates

    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
    gaste
    -0.07
    hdl
    -0.07
    ç«Ń
    -0.07
     вÑĭÑģÑĤÑĥп
    -0.06
    าศ
    -0.06
    ofs
    -0.06
    ãĤŃãĥĵ
    -0.06
    æľ¬åĬŀæ³ķ
    -0.06
     CER
    -0.06
    ä¸ĢæĽ²
    -0.06
    POSITIVE LOGITS
    以任ä½ķ
    0.07
    uban
    0.07
    è¦ģä¹Īæĺ¯
    0.07
    ambe
    0.07
     گرÙģت
    0.07
    çļĦéĢļ
    0.07
    irsch
    0.07
    zep
    0.06
     pant
    0.06
     Either
    0.06
    Activations Density 0.001%

    No Known Activations