© 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. 13016
    Prev
    Next
    INDEX
    Explanations

    Miss Universe

    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
    -0.07
     (
    -0.07
     S
    -0.07
     l
    -0.06
    verse
    -0.06
     [
    -0.06
     by
    -0.06
     .
    -0.06
     to
    -0.06
    èij
    -0.05
    POSITIVE LOGITS
     inoltre
    0.10
    èİİ士
    0.09
    转载æĪĸå¼ķçĶ¨
    0.09
    æĸ°ç¤¾
    0.09
    è¿ĺåı¯ä»¥éĢļè¿ĩ
    0.09
    åħ¬ç½ijå®īå¤ĩ
    0.09
     kenc
    0.09
    注æĦıçļĦæĺ¯
    0.08
     EUROP
    0.08
    алÑĮÑı
    0.08
    Activations Density 0.432%

    No Known Activations