© 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. 1827
    Prev
    Next
    INDEX
    Explanations

    directions and transitions

    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
    uchte
    -0.08
    ä»İä½ķ
    -0.08
    æĺ¯æĿ¥èĩª
    -0.08
    æĿ¥èĩªä¸ŃåĽ½
    -0.08
    edBy
    -0.07
    Õ¡Õ£
    -0.07
    ogy
    -0.07
    пÑĢа
    -0.07
    人åĪ°
    -0.07
    ÑĥÑīеÑģÑĤво
    -0.07
    POSITIVE LOGITS
    ORB
    0.07
    ascar
    0.07
    å±ħå¤ļ
    0.07
    ,top
    0.07
    æĪĸçĶ±
    0.06
    è´¯
    0.06
    /by
    0.06
    /left
    0.06
    èĿĩ
    0.06
    pital
    0.06
    Activations Density 0.013%

    No Known Activations