© 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. 27901
    Prev
    Next
    INDEX
    Explanations

    What is

    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
    çļĦäºĭäºĨ
    -0.08
    ä¸įçŁ¥éģĵæĢİä¹Ī
    -0.08
    ulement
    -0.07
     Extras
    -0.07
    ahas
    -0.07
    omed
    -0.07
     sic
    -0.07
    imson
    -0.07
    mony
    -0.07
    ä¸Ģè·¯ä¸Ĭ
    -0.07
    POSITIVE LOGITS
    ä¸ĭåĪĹ
    0.11
    ä¸ĭåĪĹ说æ³ķ
    0.11
     primarily
    0.09
     ____
    0.09
    ä¸ĭéĿ¢
    0.08
    ___
    0.08
    ____
    0.08
    ä¸ĭè¿°
    0.08
    æľīä¸ĭåĪĹ
    0.08
    主è¦ģ
    0.08
    Activations Density 0.023%

    No Known Activations