© 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. 44426
    Prev
    Next
    INDEX
    Explanations

    superpowers or capabilities

    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
    ostar
    -0.07
     orale
    -0.07
    ê²½
    -0.07
    اÛĮ
    -0.07
    ardı
    -0.07
    åĽ¾éĽĨ
    -0.06
    rul
    -0.06
    è¿ĻäºĽéĹ®é¢ĺ
    -0.06
     Valid
    -0.06
    åıĺæĽ´è®°å½ķ
    -0.06
    POSITIVE LOGITS
    ãģ¨ãģĦãģĨæĦıåij³
    0.08
    æĦıä¹īä¸ĬçļĦ
    0.08
    ä¸Ģç§įæĺ¯
    0.07
     Sting
    0.07
    ä»ĺ
    0.07
     بÙħعÙĨÙī
    0.07
    çļĦåIJ«ä¹ī
    0.07
    贯穿äºİ
    0.07
    ãģ®ãģĵãģ¨
    0.07
    æĤ
    0.07
    Activations Density 0.252%

    No Known Activations