© 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. 39385
    Prev
    Next
    INDEX
    Explanations

    costs money

    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
    类似äºİ
    -0.07
    urio
    -0.07
    æĹłåıĮ
    -0.06
    ër
    -0.06
    én
    -0.06
    åŁºäºİ
    -0.06
    诸
    -0.06
     übrigens
    -0.06
    mp
    -0.06
    acci
    -0.06
    POSITIVE LOGITS
    stract
    0.09
     appunto
    0.08
    rasil
    0.07
    MLS
    0.07
    代ä¹ĭ
    0.07
    QueryString
    0.07
    该款
    0.07
    iki
    0.07
    дÑĢи
    0.07
    acce
    0.07
    Activations Density 0.005%

    No Known Activations