© 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. 29737
    Prev
    Next
    INDEX
    Explanations

    source code

    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
    æĺİãģij
    -0.07
    imize
    -0.07
    -sized
    -0.07
    æĸ°çļĦ
    -0.06
    ancock
    -0.06
    ossible
    -0.06
    åij¨èº«
    -0.06
    nown
    -0.06
    zelf
    -0.06
    iswa
    -0.06
    POSITIVE LOGITS
    ural
    0.09
    ëŀĺ
    0.09
    æºIJåľ°
    0.09
     whence
    0.08
    ignan
    0.08
    ä¸įå¿į
    0.08
    okane
    0.08
    FileSync
    0.08
    unno
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
    Activations Density 0.075%

    No Known Activations