© 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. 20797
    Prev
    Next
    INDEX
    Explanations

    created by author

    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
    raft
    -0.08
    isar
    -0.08
    een
    -0.08
    uelle
    -0.07
    ses
    -0.07
     Guth
    -0.07
    Cls
    -0.07
    ¿
    -0.07
    å®Įåħ¨ä¸įåIJĮçļĦ
    -0.07
    rupt
    -0.07
    POSITIVE LOGITS
    drawer
    0.07
    便ä¼ļ
    0.07
    dert
    0.07
    ÙĥاÙħ
    0.07
    à¹Īà¸ĩ
    0.07
    elain
    0.06
    èĢĮåľ¨äºİ
    0.06
    ugs
    0.06
    Ñĩиком
    0.06
    deriv
    0.06
    Activations Density 0.014%

    No Known Activations