© 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. 8041
    Prev
    Next
    INDEX
    Explanations

    mathematical or technical terms

    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
    åľ¨è¿Ļçīĩ
    -0.07
    ä¸İ该
    -0.07
    olak
    -0.07
    ãģĤãģŁ
    -0.07
    oste
    -0.07
    æĮij
    -0.07
    æµ®äºij
    -0.07
     Erb
    -0.06
     Eid
    -0.06
    鸣
    -0.06
    POSITIVE LOGITS
    otten
    0.07
    交åĬŀçļĦ
    0.07
     ph
    0.07
    çŁŃåı¥
    0.07
    TOOLS
    0.07
     Demir
    0.06
    Ä©nh
    0.06
    ì²´ìĿ¸
    0.06
    æģ¯æģ¯
    0.06
    ripper
    0.06
    Activations Density 0.055%

    No Known Activations