© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62061
    Prev
    Next
    INDEX
    Explanations

    preface, introduction, foreword

    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
    åĪ»éª¨
    -0.08
    cier
    -0.08
    è¿Ŀæ³ķåĴĮä¸įèī¯ä¿¡æģ¯ä¸¾æĬ¥
    -0.08
    igno
    -0.08
    转载请注æĺİ
    -0.08
    átk
    -0.07
    æĭIJ
    -0.07
    RenderingContext
    -0.07
    plode
    -0.07
    LEMENT
    -0.07
    POSITIVE LOGITS
    tti
    0.08
    ç½ķ
    0.08
    endum
    0.07
    adel
    0.07
    çľŁäºº
    0.07
    _extra
    0.06
    éĥ¨åĪĨçļĦ
    0.06
     reviewers
    0.06
     special
    0.06
     sparing
    0.06
    Activations Density 0.178%

    No Known Activations