© 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. 10304
    Prev
    Next
    INDEX
    Explanations

    services, innovations, ICO, delicacies, fares

    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
    ObjectType
    -0.07
    幻影
    -0.07
    _DESCRIPTOR
    -0.06
    åĭī
    -0.06
     Bryant
    -0.06
    aisin
    -0.06
    angelo
    -0.06
    epad
    -0.06
    Ỽ
    -0.06
    zas
    -0.06
    POSITIVE LOGITS
    ãģ¨ãģĦãģĨãģĭ
    0.09
    主è¦ģæĺ¯æĮĩ
    0.09
    æĮĩçļĦæĺ¯
    0.08
    رÙĩ
    0.07
    ãģ©ãģĵãĤį
    0.07
    ICO
    0.07
    ä¸įåı¯ä»¥
    0.06
    ä¹Łä¸įå¤ļ
    0.06
    enabled
    0.06
     /^\
    0.06
    Activations Density 0.370%

    No Known Activations