© 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. 9836
    Prev
    Next
    INDEX
    Explanations

    superscripts in academic text

    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
    ation
    -0.07
     Rodr
    -0.07
    idity
    -0.06
    seite
    -0.06
    ction
    -0.06
    chow
    -0.06
    lessly
    -0.06
    ãĤĭãģ¨
    -0.06
    embali
    -0.06
    åĴĮ建议
    -0.06
    POSITIVE LOGITS
    两åѦä¸Ģåģļ
    0.09
    缸è¾ħ缸æĪIJ
    0.09
    ä¸įåı¯æĢĿè®®
    0.08
    åIJĦç§įåIJĦæł·
    0.08
    åľ¨æ´»åĬ¨ä¸Ń
    0.08
    å°ıçŁ¥è¯Ĩ
    0.08
    otella
    0.08
    身临åħ¶å¢ĥ
    0.08
    .','
    0.08
    äºĭåįĬåĬŁåĢį
    0.08
    Activations Density 0.066%

    No Known Activations