© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48717
    Prev
    Next
    INDEX
    Explanations

    saying or proverb

    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
    uard
    -0.09
    зни
    -0.08
    -caret
    -0.08
    inger
    -0.08
    óx
    -0.08
     Amid
    -0.08
    éļĽ
    -0.08
    寵
    -0.08
    ÑĤали
    -0.08
    碩
    -0.08
    POSITIVE LOGITS
    çĥ
    0.07
    èµ°éģį
    0.07
    æĹ©çŁ¥éģĵ
    0.07
    ä¸īåĪĨ
    0.06
    æ°¸ä¸į
    0.06
    ä¸īå®Ŀ
    0.06
    æĦıæĮĩ
    0.06
    æľīä¸ī
    0.06
    å®ģåı¯
    0.06
    Native
    0.06
    Activations Density 0.038%

    No Known Activations