© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62046
    Prev
    Next
    INDEX
    Explanations

    differ and variations

    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
    icka
    -0.08
    Registrar
    -0.07
     Cunningham
    -0.07
     Pob
    -0.07
    ä¼ĺåĬ¿
    -0.07
    Categ
    -0.07
    fü
    -0.06
    大éĥ¨ä»½
    -0.06
     DEM
    -0.06
    eree
    -0.06
    POSITIVE LOGITS
    çļĦä¸įåIJĮ
    0.15
    ä¸įåIJĮçļĦæĺ¯
    0.15
     differing
    0.14
     differs
    0.14
    à¸ķà¹Īาà¸ĩà¸ģัà¸Ļ
    0.14
     differently
    0.13
     unterschied
    0.13
    æľīæīĢä¸įåIJĮ
    0.13
     differ
    0.13
    à¸Ĺีà¹Īà¹ģà¸ķà¸ģà¸ķà¹Īาà¸ĩà¸ģัà¸Ļ
    0.13
    Activations Density 0.447%

    No Known Activations