© 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. 4269
    Prev
    Next
    INDEX
    Explanations

    numbers followed by things

    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
    reif
    -0.07
     direct
    -0.06
    åIJĪæĪIJ
    -0.06
     lit
    -0.06
     fusion
    -0.06
    æĢªä¸įå¾Ĺ
    -0.06
    FY
    -0.06
    é¼ĵèĪŀ
    -0.06
    æ±ĤçĶŁ
    -0.06
    åIJ¸å¼ķçĿĢ
    -0.06
    POSITIVE LOGITS
    èĩªæĦ¿
    0.10
    åĪĨæĪIJ
    0.10
    两ç»Ħ
    0.09
    å¹´é¾Ħåľ¨
    0.09
     ëĮĢìĥģìľ¼ë¡ľ
    0.09
    éļıæľº
    0.09
     randomly
    0.09
    åĪĨç»Ħ
    0.09
    æ¯ıç»Ħ
    0.08
    éļ¨æ©Ł
    0.08
    Activations Density 0.797%

    No Known Activations