© 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. 46527
    Prev
    Next
    INDEX
    Explanations

    for males, females, children, adults

    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
    ä¹Łä¸įåIJĮ
    -0.07
    Ĥ
    -0.07
    ãģ¹ãģı
    -0.07
    åĽ¢çļĦ
    -0.06
    дие
    -0.06
    çļĦ鼨
    -0.06
    ekin
    -0.06
    ä¸ĸçļĦ
    -0.06
    atu
    -0.06
    <<<<<<<
    -0.06
    POSITIVE LOGITS
    å·¦åı³çļĦ
    0.08
    елÑı
    0.08
    æīĭå¿ĥ
    0.08
    onen
    0.07
    à¹Ģลยà¸Ĺีà¹Ģà¸Ķียว
    0.07
    าà¸Ĺี
    0.07
    ÑģÑĤика
    0.07
     principal
    0.07
    elsius
    0.07
    ä¹ĭå¤ļ
    0.07
    Activations Density 0.194%

    No Known Activations