© 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. 55861
    Prev
    Next
    INDEX
    Explanations

    academic publication dates

    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
    utr
    -0.07
    ä¸ĩå²ģ
    -0.07
    trl
    -0.07
    ạt
    -0.07
    è¿Ļä¸Ģå¹´
    -0.07
    ×ĺ×Ķ
    -0.07
    ikel
    -0.07
    ثر
    -0.06
    ä¸ĢæľĪ
    -0.06
    æѤæŶ
    -0.06
    POSITIVE LOGITS
    è¿ijå¹´
    0.07
    åıĮåĩı
    0.07
    åľ¨åݻ年
    0.07
    ÑģлÑı
    0.07
    æĸ°åĨł
    0.07
    recent
    0.07
    entuk
    0.07
    æľĢæĹ©çļĦ
    0.06
    åĿĩåľ¨
    0.06
    æĸ°åĨłèĤºçĤİ
    0.06
    Activations Density 1.084%

    No Known Activations