© 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. 54968
    Prev
    Next
    INDEX
    Explanations

    how to fix it

    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
    å¿ı
    -0.08
    stantiate
    -0.07
    天ä»Ļ
    -0.07
    ÐľÐļ
    -0.07
    æľªå¤®
    -0.07
    çļĦå°ıç¼ĸ
    -0.07
    第åįģäºĮç«ł
    -0.07
    æ¦Ķ
    -0.07
    <Real
    -0.07
    ode
    -0.07
    POSITIVE LOGITS
     reliably
    0.10
    æŃ£ç¢º
    0.08
    æŃ£ç¡®å¤ĦçIJĨ
    0.08
    æĽ´å®īåħ¨
    0.07
     zuverläss
    0.07
     alternatives
    0.07
     safely
    0.07
    åı¯éĿłçļĦ
    0.07
    åı¯éĿł
    0.07
     universally
    0.07
    Activations Density 0.034%

    No Known Activations