© 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. 10173
    Prev
    Next
    INDEX
    Explanations

    class action, docRoot, day visit

    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
    gon
    -0.08
    é¾Ł
    -0.07
    гоÑĢа
    -0.07
    çĭĻ
    -0.07
    ouns
    -0.07
    amaz
    -0.07
    å±Ģéĥ¨
    -0.07
     Benedict
    -0.06
     gra
    -0.06
    gun
    -0.06
    POSITIVE LOGITS
    æ¬
    0.08
    æĺ¯è¿Ļæł·çļĦ
    0.08
    éĢ¢
    0.08
    æ²īçĿĢ
    0.08
    ä¸įæĮī
    0.07
    åı£æīį
    0.07
    骨çļĦ
    0.07
    顽强
    0.07
    Scrollbar
    0.07
    lime
    0.07
    Activations Density 0.028%

    No Known Activations