© 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. 39853
    Prev
    Next
    INDEX
    Explanations

    works as

    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
    追究åħ¶
    -0.07
    ittings
    -0.07
    lobber
    -0.07
     appunto
    -0.07
    здÑĢа
    -0.07
    зÑĭк
    -0.07
    ìĬ¨
    -0.07
    个个
    -0.07
    zheimer
    -0.07
    ystick
    -0.06
    POSITIVE LOGITS
    å°±è¿Ļæł·
    0.08
    yw
    0.07
    äºĮæĺ¯è¦ģ
    0.07
    çļĦåħ¶ä»ĸ
    0.07
    äºĮæĺ¯
    0.07
     Misc
    0.07
    åħ¶äºĮ
    0.07
    æ´»åĬ¨ç»ĵæĿŁåIJİ
    0.06
    yje
    0.06
    åİŁåĪĻä¸Ĭ
    0.06
    Activations Density 0.702%

    No Known Activations