© 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. 59033
    Prev
    Next
    INDEX
    Explanations

    multiple choice letter followed by parenthesis

    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
    anza
    -0.08
    ä»»åĬ³ä»»æĢ¨
    -0.07
    ازÙĩ
    -0.07
    _PREVIEW
    -0.07
    æľªå°½
    -0.07
    foobar
    -0.07
    åĨĻå¾Ĺ
    -0.07
    éĹ®é¢ĺæŶ
    -0.06
     tyt
    -0.06
     rued
    -0.06
    POSITIVE LOGITS
    ãģĵãģ¨ãĤĦ
    0.07
    ãĢıãĢİ
    0.07
    uptools
    0.07
    ï¸ı
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.06
    ï¼īãĢģ
    0.06
    inate
    0.06
    
    0.06
    )ãĢģ
    0.06
     activeClassName
    0.06
    Activations Density 0.001%

    No Known Activations