© 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. 58336
    Prev
    Next
    INDEX
    Explanations

    identifiers or special contexts

    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
    undet
    -0.08
    _ANY
    -0.08
    ç¥ŀçİĭ
    -0.08
    resume
    -0.07
    æĹłèĻij
    -0.07
     Frucht
    -0.07
    Matchers
    -0.07
    à¹Ĥà¸ļ
    -0.07
    дÑĢи
    -0.07
    zeb
    -0.07
    POSITIVE LOGITS
    efore
    0.07
    ehir
    0.07
    å°±è¿Ļæł·
    0.07
    æııåĨĻ
    0.07
    ime
    0.07
     hoped
    0.07
    æıı
    0.07
     ÙģÙĦ
    0.06
    å¯ĵ
    0.06
    èµĸ以
    0.06
    Activations Density 0.009%

    No Known Activations