© 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. 40796
    Prev
    Next
    INDEX
    Explanations

    scaling or normalization of values

    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
    Mask
    -0.07
    ä¸įåĸĦ
    -0.07
    _mask
    -0.07
    _guard
    -0.07
    >J
    -0.07
    æĶ¯æĮģåĬĽåº¦
    -0.07
     Jag
    -0.07
     Mask
    -0.07
    дÑĮ
    -0.06
    å¤ĸåĽ½è¯ŃåŃ¦æł¡
    -0.06
    POSITIVE LOGITS
     normalized
    0.10
    normalized
    0.10
    caled
    0.10
     scaled
    0.10
     normalization
    0.10
    scaled
    0.09
    æ¯Ķä¾ĭ
    0.09
    .normalize
    0.09
     scaling
    0.09
    缩æĶ¾
    0.09
    Activations Density 0.010%

    No Known Activations