© 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. 13291
    Prev
    Next
    INDEX
    Explanations

    Scottish blood; rise; AlyGaN; cocoa solids; water content

    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
    insky
    -0.07
    inski
    -0.07
    .easy
    -0.07
    jas
    -0.06
    aset
    -0.06
    建ç«ĭ
    -0.06
    çªŁ
    -0.06
    è§Ħ模çļĦ
    -0.06
    è·¨çľģ
    -0.06
    æĮģç»Ń
    -0.06
    POSITIVE LOGITS
    æ¯Ķä¾ĭ
    0.10
    æ¯Ķä¾ĭçļĦ
    0.10
     proportion
    0.09
    æĪIJåĪĨçļĦ
    0.09
    æ¯Ķä¾ĭ为
    0.09
    çļĦæ¯Ķä¾ĭ
    0.09
    æĪIJ份
    0.09
    %%%%
    0.09
    æĪIJåĪĨ
    0.09
     долÑı
    0.08
    Activations Density 0.002%

    No Known Activations