© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58951
    Prev
    Next
    INDEX
    Explanations

    code separators and structure

    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
    Negative Logits
    ult
    -0.08
    ä¸ĭåIJĮ
    -0.07
    大åı¯
    -0.07
    ä¸įä¼ij
    -0.07
    иÑģÑĤÑĢи
    -0.06
    ai
    -0.06
    ajakan
    -0.06
    ä¸Ģå®ļçļĦ
    -0.06
     cierto
    -0.06
    reta
    -0.06
    POSITIVE LOGITS
    ehm
    0.07
    åĽ½ä¹ĭ
    0.07
    волÑĮ
    0.07
    ä¼ĹæīĢåij¨çŁ¥
    0.07
    plevel
    0.07
    ugs
    0.06
    ...',
    0.06
    żÄħ
    0.06
    abar
    0.06
    è¡¥çŁŃ
    0.06
    Activations Density 0.041%

    No Known Activations