© 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. 18465
    Prev
    Next
    INDEX
    Explanations

    while loops

    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
    oland
    -0.08
    utar
    -0.08
    ÑĥÑĤа
    -0.08
    èĻ½å°ı
    -0.08
    æĹ¢çĦ¶æĺ¯
    -0.08
    vsp
    -0.07
    è¿ĻæŶçļĦ
    -0.07
    è¯ĿæĿ¥
    -0.07
    ahan
    -0.07
    edale
    -0.07
    POSITIVE LOGITS
    ä¸įæģ¯
    0.08
    ä¸įä¼ij
    0.08
    inery
    0.06
    çĹ
    0.06
    меÑģÑĤ
    0.06
    inen
    0.06
    ŀ
    0.06
    èĸ
    0.06
    ä¸įèĪį
    0.06
    ?):
    0.06
    Activations Density 0.006%

    No Known Activations