© 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. 22626
    Prev
    Next
    INDEX
    Explanations

    text after body

    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
    æĢ»ä½ĵè¦ģæ±Ĥ
    -0.07
    oses
    -0.07
    çªĿéĩĮ
    -0.07
    ëĮ
    -0.07
    ynes
    -0.07
    ocks
    -0.06
    .exports
    -0.06
    rv
    -0.06
    fek
    -0.06
    åĵģçļĦ
    -0.06
    POSITIVE LOGITS
    ä¹Łç¡®å®ŀ
    0.09
     explicitly
    0.09
    è¿Ŀåıįä¸Ĭè¿°
    0.09
    æĺİç¡®
    0.08
    ä¸Ĭè¿°
    0.08
    确认
    0.08
    对ä¸Ĭè¿°
    0.08
    explicit
    0.08
    çļĦç¡®
    0.08
    æĺİ确表示
    0.07
    Activations Density 0.192%

    No Known Activations