© 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. 48933
    Prev
    Next
    INDEX
    Explanations

    literacy rate

    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
    为åIJĮåѦ们
    -0.08
    uve
    -0.08
    åĴĮåIJĮåѦ
    -0.07
     ($.
    -0.07
    ä¼ĺç§ĢåѦçĶŁ
    -0.07
    InstanceOf
    -0.07
    éĹŃéŨ
    -0.07
    uva
    -0.07
    ä¸İåIJĮåѦ
    -0.07
    ÑĢÑĥг
    -0.07
    POSITIVE LOGITS
    æĻ®åıĬ
    0.13
     literacy
    0.11
    åIJ¯èĴĻ
    0.09
    è¯ĨåŃĹ
    0.09
    éĢĤé¾Ħ
    0.08
    年满
    0.08
     baud
    0.07
     census
    0.07
    -enabled
    0.07
    åªĴ
    0.07
    Activations Density 0.056%

    No Known Activations