© 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. 19451
    Prev
    Next
    INDEX
    Explanations

    enumerated lists or fragments

    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
    taki
    -0.08
    æľīä»»ä½ķçĸijéĹ®
    -0.08
    ä¸į误
    -0.07
    nameof
    -0.07
    erald
    -0.07
    æĸĩåĮĸçŁ¥è¯Ĩ
    -0.07
    º¼
    -0.07
    çļĦå°ıä¼Ļ伴们
    -0.07
    elat
    -0.07
    alone
    -0.07
    POSITIVE LOGITS
    è¿Ļ个æķ°åŃĹ
    0.12
    ãģĨãģ¡
    0.11
     altrett
    0.09
    æĢ»åħ±
    0.09
    ä¹ĭå¤ļ
    0.09
    æĢ»æķ°
    0.09
    ìĶ©
    0.08
    ãģĨãģ¡ãģ®
    0.08
    缺ä¸Ģä¸įåı¯
    0.08
    åĴĮä¸Ģ个
    0.08
    Activations Density 0.346%

    No Known Activations