© 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. 21037
    Prev
    Next
    INDEX
    Explanations

    gold particles

    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
    Ĺ
    -0.08
    à¸Ļà¸Ńà¸ĩ
    -0.07
     bottled
    -0.07
    ulis
    -0.07
    ych
    -0.07
    à·Ģà·ı
    -0.06
    -session
    -0.06
    -ev
    -0.06
     espon
    -0.06
    _iteration
    -0.06
    POSITIVE LOGITS
    对åIJĦ
    0.07
    æī®
    0.07
    ouden
    0.07
    é¦ĸåħĪåľ¨
    0.07
    åĴĮåIJĦ
    0.07
    IfNeeded
    0.07
    à¹ģà¸Ļà¸Ļ
    0.07
    èĢħä¼ĺåħĪ
    0.06
    bury
    0.06
     bevorzug
    0.06
    Activations Density 0.056%

    No Known Activations