© 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. 29378
    Prev
    Next
    INDEX
    Explanations

    PER CURIAM

    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
    好åIJĹ
    -0.07
    为æĤ¨çļĦ
    -0.07
    ihal
    -0.07
    agon
    -0.07
    egas
    -0.07
     onPage
    -0.07
    esen
    -0.06
    usin
    -0.06
    èĪĮå°ĸ
    -0.06
    ÛĮÙĦ
    -0.06
    POSITIVE LOGITS
    èĻ½çĦ¶æľī
    0.07
    åĢ¼å¾Ĺ注æĦıçļĦæĺ¯
    0.07
    天ä¸ĭ第ä¸Ģ
    0.07
    ertes
    0.07
    éľĢè¦ģ注æĦıçļĦæĺ¯
    0.07
    èĻ½çĦ¶
    0.07
    quet
    0.07
    yj
    0.07
    为äºĨå®ŀçİ°
    0.07
    æľĢéļ¾
    0.07
    Activations Density 0.504%

    No Known Activations