© 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. 52213
    Prev
    Next
    INDEX
    Explanations

    Vietnam and Vietnamese words

    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
    éħį以
    -0.07
     subrange
    -0.06
     Tratt
    -0.06
    اÙĨد
    -0.06
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.06
    çļĨåı¯
    -0.06
    俯çŀ°
    -0.06
     reag
    -0.05
     Ol
    -0.05
     consequ
    -0.05
    POSITIVE LOGITS
    .vn
    0.10
    æ´»åĬ¨çļĦå¼Ģå±ķ
    0.08
     viet
    0.08
     trần
    0.08
     Viet
    0.08
     Angeb
    0.08
    uchen
    0.08
    ckt
    0.07
    è¶ĬåįĹ
    0.07
     ê¹Į
    0.07
    Activations Density 0.036%

    No Known Activations