© 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. 22539
    Prev
    Next
    INDEX
    Explanations

    data structures: hashes, dictionaries, lists, tuples, maps

    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
    mer
    -0.07
    y
    -0.07
    æģIJ
    -0.07
    ä¸Ĭå¸Ĥ
    -0.07
    je
    -0.06
    á»ĥn
    -0.06
    reat
    -0.06
     itself
    -0.06
     humble
    -0.06
    ful
    -0.06
    POSITIVE LOGITS
    çīĪæĿĥä¸İåħį责声æĺİ
    0.08
    ìĶ©
    0.08
    tring
    0.08
    ายà¸Ļ
    0.08
    ä¸įåIJĮç¨ĭ度çļĦ
    0.08
    неÑĢа
    0.08
    à¸ĺิ
    0.07
     sublist
    0.07
    (each
    0.07
    Likes
    0.07
    Activations Density 0.014%

    No Known Activations