© 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. 2126
    Prev
    Next
    INDEX
    Explanations

    geometric shapes, money, or division

    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
     appunto
    -0.09
    rang
    -0.07
    ä¹Łç¡®å®ŀ
    -0.07
    মà§ĩ
    -0.07
    åIJĪåIJĮå±¥è¡Į
    -0.07
     indeed
    -0.07
    çļĦç¡®æĺ¯
    -0.07
    okal
    -0.07
    _dl
    -0.06
    quiries
    -0.06
    POSITIVE LOGITS
    æĪĸèĢħåħ¶ä»ĸ
    0.08
    æĪĸèĢħæľī
    0.07
     somehow
    0.07
    ssid
    0.07
    æĺ¯ä¸ª
    0.07
    æ¯Ķå¦Ĥ说
    0.06
    .Then
    0.06
    æĪĸèĢħæĺ¯
    0.06
    æĪĸèĢħ
    0.06
    idor
    0.06
    Activations Density 0.008%

    No Known Activations