© 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. 12585
    Prev
    Next
    INDEX
    Explanations

    offset, long, UTC

    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
    ys
    -0.08
     Hub
    -0.07
    仪
    -0.07
    Hub
    -0.07
    é¦Ĩ
    -0.07
    ä¼´ä½ł
    -0.07
    ãģ³
    -0.07
    ale
    -0.06
    alli
    -0.06
    erv
    -0.06
    POSITIVE LOGITS
    elop
    0.08
    ifat
    0.08
    uelle
    0.07
    itants
    0.07
    ixer
    0.07
    å±ŀæĢ§çļĦ
    0.07
    æľīæĸĻ
    0.07
    ÑĢиÑģÑĤа
    0.07
    strar
    0.07
    iards
    0.07
    Activations Density 0.006%

    No Known Activations