© 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. 64084
    Prev
    Next
    INDEX
    Explanations

    code and script tags

    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
    ($(".
    -0.07
    åģĩ
    -0.07
     Cama
    -0.07
     Fras
    -0.07
    enne
    -0.07
    à®ķà¯įà®ķà¯ģà®®à¯į
    -0.07
    istant
    -0.06
    åĪĿ级
    -0.06
    æIJŃ
    -0.06
    è´¾
    -0.06
    POSITIVE LOGITS
    åħ¨ç«Ļ
    0.07
    èıı
    0.07
     dure
    0.07
    InView
    0.07
    翱
    0.07
    rets
    0.07
    berto
    0.07
    寮
    0.07
    çŃīå¹³åı°
    0.07
    æł·å¼ı
    0.07
    Activations Density 0.004%

    No Known Activations