© 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. 50435
    Prev
    Next
    INDEX
    Explanations

    inaugural speech, debut single, cabinet of, exited the house, fish tank, musical tastes, with the cousins, finish education, my local setup

    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
    /vnd
    -0.08
    ORO
    -0.08
    oro
    -0.07
    广大çļĦ
    -0.07
     ÏĢÏģÏĮ
    -0.07
    å¾ĭ
    -0.07
    ÙĪات
    -0.07
    ä»ģ
    -0.07
    uz
    -0.07
    ]")
    -0.07
    POSITIVE LOGITS
    áŀļáŀĶ
    0.09
    à¸Ĥà¸Ńà¸ĩà¸ķà¸Ļ
    0.09
    inya
    0.09
    æ
    0.08
    ys
    0.08
    à¸Ĥà¸Ńà¸ĩà¸Ĺà¹Īาà¸Ļ
    0.07
    à¸Ĥà¸Ńà¸ĩà¹Ģà¸ĺà¸Ń
    0.07
    çħľ
    0.07
    à¸Ĥà¸Ńà¸ĩà¹Ģà¸Ĥา
    0.07
    æīij
    0.07
    Activations Density 0.848%

    No Known Activations