© 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. 1845
    Prev
    Next
    INDEX
    Explanations

    captain, leader, chairman

    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
    Ð¢ÐŁ
    -0.07
    ึà¸ģ
    -0.07
    ody
    -0.07
    tring
    -0.07
    ÙĨÙĬÙĩ
    -0.07
    alu
    -0.07
    ções
    -0.07
    à¸IJาà¸Ļ
    -0.07
    oundation
    -0.07
    为åİŁæĸĻ
    -0.07
    POSITIVE LOGITS
    带é¢Ĩ
    0.11
    azgo
    0.11
    带é¢Ĩä¸ĭ
    0.10
     overseeing
    0.10
    ¸
    0.10
    ãĤĴåĭĻ
    0.09
    å¼ķé¢Ĩ
    0.09
    æīĭä¸ĭ
    0.09
    çļĦ带é¢Ĩä¸ĭ
    0.08
    ä¸ĢèģĮ
    0.08
    Activations Density 0.352%

    No Known Activations