© 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. 63990
    Prev
    Next
    INDEX
    Explanations

    oxide, Manufacturer, cells, examinations

    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
    ocking
    -0.07
     shell
    -0.06
    st
    -0.06
    ç´¢
    -0.06
    ä¹ĭåıĪ
    -0.06
    滩
    -0.06
     theatrical
    -0.06
    rib
    -0.06
    ien
    -0.06
    shell
    -0.06
    POSITIVE LOGITS
    cheiden
    0.08
    æł·ä¾ĭ
    0.08
    erland
    0.08
     esempio
    0.07
    εια
    0.07
     поÑģледÑĥ
    0.07
    å°±æĺ¯ä¸Ģ个
    0.07
    adÄĽ
    0.07
    omla
    0.07
    stadt
    0.07
    Activations Density 0.116%

    No Known Activations