© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22261
    Prev
    Next
    INDEX
    Explanations

    known in the art

    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
    ä¹Łåı«
    -0.08
    полÑĥ
    -0.08
     Ãģngeles
    -0.08
    æł¸åĩĨæĹ¥æľŁ
    -0.07
    ä½łå¯¹è¿Ļ个åĽŀçŃĶçļĦè¯Ħä»·æĺ¯
    -0.07
    abora
    -0.07
    æĭ¥
    -0.07
    ä»ĸä¿©
    -0.07
    Че
    -0.07
     trách
    -0.07
    POSITIVE LOGITS
     herein
    0.10
     patent
    0.10
     Patent
    0.08
    ä¸ĵåĪ©
    0.08
    çİ°æľīæĬĢæľ¯
    0.08
     patents
    0.08
     pursuant
    0.07
    ette
    0.07
     embodiments
    0.07
     inventions
    0.07
    Activations Density 1.720%

    No Known Activations