© 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. 46518
    Prev
    Next
    INDEX
    Explanations

    names followed by numbers or titles

    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
    两ç§įæĸ¹å¼ı
    -0.07
    åįķçļĦ
    -0.06
    Ju
    -0.06
     Pruitt
    -0.06
    æµĨ
    -0.06
    åĦ¿çļĦ
    -0.06
     Katz
    -0.06
    eyJ
    -0.06
    èİ«éĿŀ
    -0.06
    hr
    -0.06
    POSITIVE LOGITS
    å§ĭèĩ³
    0.08
    xBE
    0.08
    訴
    0.08
    丽人
    0.08
    anyl
    0.07
    anser
    0.07
    Į¨
    0.07
    lik
    0.07
    äsch
    0.07
    ÑĤай
    0.07
    Activations Density 0.006%

    No Known Activations