© 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. 18406
    Prev
    Next
    INDEX
    Explanations

    mean age of years

    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
    oul
    -0.07
    azzi
    -0.06
    getC
    -0.06
    tek
    -0.06
    æĿĢ害
    -0.06
    ä¸ŃèĦ±é¢ĸèĢĮåĩº
    -0.06
    æİIJ
    -0.06
    cf
    -0.06
    åłª
    -0.06
     Coff
    -0.05
    POSITIVE LOGITS
    åģı
    0.10
    ognito
    0.09
    Bias
    0.09
    atico
    0.08
    _coin
    0.08
    Destructor
    0.08
     Bias
    0.08
    LayoutManager
    0.08
    bias
    0.08
    -hooks
    0.08
    Activations Density 0.023%

    No Known Activations