© 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. 51610
    Prev
    Next
    INDEX
    Explanations

    (i)

    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
    bole
    -0.07
    к
    -0.07
    æĸ¹æĸ¹éĿ¢
    -0.07
    ——
    -0.07
    —or
    -0.07
    æĪĸèĢħæľī
    -0.07
     rued
    -0.07
    æĪĸ被
    -0.06
    ynd
    -0.06
    并éĿŀæĺ¯
    -0.06
    POSITIVE LOGITS
    .*,
    0.10
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.08
    "",
    0.08
     Redistributions
    0.07
    =?,
    0.07
     ÑģобÑģÑĤвенно
    0.07
    ascar
    0.07
    ãĢıãĢİ
    0.07
    ãģªãģıãģªãĤĬ
    0.07
    #",
    0.07
    Activations Density 0.032%

    No Known Activations