© 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. 46826
    Prev
    Next
    INDEX
    Explanations

    expectation of

    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
    s
    -0.09
    bing
    -0.08
    λεÏħ
    -0.07
    ãģıãģªãģĦ
    -0.07
    ÙĦ
    -0.07
    HING
    -0.07
    ãģĦãĤĭ
    -0.07
    zeti
    -0.07
    te
    -0.07
    र
    -0.06
    POSITIVE LOGITS
    åħ¼æĢ»ç»ıçIJĨ
    0.09
    ful
    0.09
    µ
    0.09
    uries
    0.08
     vặt
    0.08
    à¸ģารà¸ĵà¹Į
    0.08
     thoại
    0.08
    AsString
    0.08
    åĴĮ建议
    0.08
    stüt
    0.08
    Activations Density 0.004%

    No Known Activations