© 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. 55588
    Prev
    Next
    INDEX
    Explanations

    maximum dose, concentration, value

    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
    à¹īาย
    -0.08
    ç§įç±»ç¹ģå¤ļ
    -0.08
    áĥIJáĥĻ
    -0.07
    è¿Ļç§įä¸ľè¥¿
    -0.07
    isser
    -0.07
    kten
    -0.07
    åĩłä¸ĩ
    -0.07
    rava
    -0.07
    áĢĽáĢ¾
    -0.07
    åĬ¨è¾Ħ
    -0.07
    POSITIVE LOGITS
    è¿Ļ个æķ°åŃĹ
    0.11
    typ
    0.08
    ãģķãģĻãģĮ
    0.07
     corresponds
    0.07
    çĶ¨æĿ¥
    0.07
    约åIJĪ
    0.07
    éĴŀ
    0.07
    ÑģÑĤан
    0.07
     Wag
    0.06
     Represents
    0.06
    Activations Density 0.130%

    No Known Activations