© 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. 7155
    Prev
    Next
    INDEX
    Explanations

    explaining or adding detail

    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
    Extern
    -0.08
    çļĦè¿Ļç§į
    -0.07
    ä»Ķç»Ĩåľ°
    -0.07
    agen
    -0.07
    åħ·æľī以ä¸ĭ
    -0.07
     carefully
    -0.07
    ẩn
    -0.07
    缴æİ¥æĪĸ
    -0.07
    åIJĦå¼ıåIJĦæł·çļĦ
    -0.07
    adf
    -0.07
    POSITIVE LOGITS
     further
    0.08
    ikul
    0.07
     scope
    0.07
     credibility
    0.07
    æĽ´åĬłå¼º
    0.07
    åį°è¯ģ
    0.07
     context
    0.07
    çī¹èģĺ
    0.07
    ä¸Ģ并
    0.07
    scope
    0.07
    Activations Density 0.024%

    No Known Activations