© 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. 43230
    Prev
    Next
    INDEX
    Explanations

    you read that right

    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
    æĤī
    -0.08
    orman
    -0.08
    ooter
    -0.07
    éģĵ
    -0.07
    å½¢èī²
    -0.07
    orma
    -0.07
    è¿ĺ没æĿ¥å¾ĹåıĬ
    -0.07
    Mixin
    -0.07
    orm
    -0.06
    ords
    -0.06
    POSITIVE LOGITS
    å¥ĩæĢª
    0.08
     ê·¸ëĮĢë¡ľ
    0.07
    åı¦ç±»
    0.07
    羣æľī
    0.07
     unusual
    0.07
    ansk
    0.07
     ungewöhn
    0.07
    æĿŁæīĭ
    0.07
    è®¤çľŁçļĦ
    0.07
     insist
    0.07
    Activations Density 0.015%

    No Known Activations