© 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. 31849
    Prev
    Next
    INDEX
    Explanations

    medical context, results, numbers

    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
    çijŀæĭī
    -0.09
    ajari
    -0.09
    ansir
    -0.08
    åıĹè¿ĩ
    -0.07
    Ụ
    -0.07
    ocop
    -0.07
    ç«ŀåĵģä¿¡æģ¯
    -0.07
    ارÙĩ
    -0.07
     Vui
    -0.07
    [`
    -0.07
    POSITIVE LOGITS
    /comment
    0.07
    讨
    0.07
    pap
    0.06
    è¨İ
    0.06
     itself
    0.06
    ä¸ĩ人
    0.06
    gers
    0.06
    upe
    0.06
    lder
    0.06
    ÅĽnie
    0.06
    Activations Density 0.006%

    No Known Activations