© 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. 7148
    Prev
    Next
    INDEX
    Explanations

    exchange or swap

    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
    åĬ³
    -0.08
    对æķ´ä¸ª
    -0.08
    usen
    -0.07
    è¿ĺæĺ¯ä¸į
    -0.07
    注åĨĮæŶéĹ´
    -0.07
    ãģŁãģŁ
    -0.07
    Inflater
    -0.07
    -cert
    -0.07
    ç«ĭãģ¡
    -0.07
    .Done
    -0.07
    POSITIVE LOGITS
    Exchange
    0.09
    ç½®æį¢
    0.09
    äºĴæį¢
    0.09
    交æį¢
    0.09
     exchanged
    0.09
     Exchange
    0.09
     exchange
    0.09
    æį¢æĿ¥çļĦ
    0.08
    swap
    0.08
     swapped
    0.08
    Activations Density 0.022%

    No Known Activations