© 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. 59052
    Prev
    Next
    INDEX
    Explanations

    body tag and content

    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
    aggi
    -0.09
    ered
    -0.07
    ../../../
    -0.07
    žno
    -0.07
    åı·ä»¤
    -0.07
    iez
    -0.07
    رÙĩ
    -0.07
    æļ´
    -0.07
    оз
    -0.07
    aggio
    -0.06
    POSITIVE LOGITS
    å¨ĺå¨ĺ
    0.08
    æĤ¼
    0.08
    åĴĮé£İéĻ©
    0.08
    åįģ足
    0.08
     plain
    0.07
    Ñĥз
    0.07
    ä¸įæĸŃ丰å¯Į
    0.07
    满满
    0.07
    voll
    0.07
    åĨħ容çļĦ
    0.07
    Activations Density 0.043%

    No Known Activations