© 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. 43285
    Prev
    Next
    INDEX
    Explanations

    African Americans or women

    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
    åĨ³æĸĹ
    -0.08
    iami
    -0.08
    å¾Īä½İ
    -0.07
    .createServer
    -0.07
    åıªå¾Ĺ
    -0.07
    olib
    -0.07
    ook
    -0.07
    主è¦ģæĺ¯éĢļè¿ĩ
    -0.07
    便åı¯
    -0.07
    åı¯è¨Ģ
    -0.07
    POSITIVE LOGITS
    è¦ģæ¯Ķ
    0.15
    ãģ®æĸ¹ãģĮ
    0.15
    ãģ®ãģ»ãģĨãģĮ
    0.14
    ãģ»ãģĨãģĮ
    0.14
    æ¯Ķ
    0.13
    ä¼ļæ¯Ķ
    0.13
    缸è¾ĥäºİ
    0.12
    ä¼ĺäºİ
    0.12
    éĥ½æ¯Ķ
    0.12
    è¿ľæ¯Ķ
    0.11
    Activations Density 0.181%

    No Known Activations