© 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. 48017
    Prev
    Next
    INDEX
    Explanations

    after stroke: the development

    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
    è¨Ģä¹ĭ
    -0.08
    ¡
    -0.07
    ippi
    -0.07
    涯
    -0.07
     downhill
    -0.07
     Jennings
    -0.06
    æĭ¯
    -0.06
    æĢªçļĦ
    -0.06
    ãģłãģĭãĤī
    -0.06
    visions
    -0.06
    POSITIVE LOGITS
    /on
    0.10
    /of
    0.08
    باد
    0.07
    ä¸Ģæīĭ
    0.07
    à·Ħ
    0.06
    ัà¸ĩà¸ģ
    0.06
    座åı³
    0.06
    åįģ大
    0.06
    omu
    0.06
    èĢĮåľ¨
    0.06
    Activations Density 0.148%

    No Known Activations