© 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. 38629
    Prev
    Next
    INDEX
    Explanations

    Coca Cola

    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
    гÑĢи
    -0.09
    hani
    -0.09
     levering
    -0.08
     rectific
    -0.08
     ÑĢазÑĭ
    -0.08
    ipp
    -0.07
    кновен
    -0.07
    indy
    -0.07
    WITHOUT
    -0.07
    åıĬè¦ģæ±Ĥ
    -0.07
    POSITIVE LOGITS
     nonetheless
    0.07
    -dominated
    0.07
    没åĬŀæ³ķ
    0.07
    åĭī强
    0.07
    -sup
    0.07
    ä»įèĥ½
    0.07
    ä½Ĩåı¯ä»¥
    0.07
    åİŁæľ¬çļĦ
    0.06
    ä»įåľ¨
    0.06
     Nonetheless
    0.06
    Activations Density 0.253%

    No Known Activations