© 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. 29266
    Prev
    Next
    INDEX
    Explanations

    scientific citations with volume.pages

    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
    è¿ĽéĢĢ
    -0.07
    vih
    -0.07
    vron
    -0.07
    身
    -0.07
    -China
    -0.07
    гÑĢÑĥзки
    -0.06
    _eval
    -0.06
     tuber
    -0.06
     conspic
    -0.06
    hausen
    -0.06
    POSITIVE LOGITS
     Astroph
    0.08
    оÑĢÑı
    0.08
     Err
    0.08
     Flavor
    0.08
    Err
    0.08
    人马
    0.08
    æĸ°åħī
    0.07
    į¼
    0.07
     Phys
    0.07
    奶çĪ¸
    0.07
    Activations Density 0.088%

    No Known Activations