© 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. 51016
    Prev
    Next
    INDEX
    Explanations

    -specific, -based, -dependent, -centric qualifiers

    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
    ä¸įå®ĮçļĦ
    -0.09
    ä¸Ńæľī
    -0.09
    æīĢåľ¨
    -0.08
    ×ķ׳×Ļ
    -0.08
    ä¸Ń人
    -0.07
    ish
    -0.07
    otor
    -0.07
    以å¾ħ
    -0.07
    ier
    -0.07
    itier
    -0.07
    POSITIVE LOGITS
    zte
    0.08
    iated
    0.08
    iven
    0.08
    abouts
    0.08
    ÙĨدÛĮ
    0.07
    ÑĤоÑĢаÑı
    0.07
    ãģ¨æĢĿãĤıãĤĮãĤĭ
    0.07
    ä¸Ķåľ¨
    0.07
    gether
    0.07
    IVEN
    0.07
    Activations Density 0.229%

    No Known Activations