© 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. 6972
    Prev
    Next
    INDEX
    Explanations

    Russian and Slovenian word fragments

    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
    اÙĭ
    -0.09
    ation
    -0.09
    Ùĭا
    -0.08
    æĦıä¹īä¸ĬçļĦ
    -0.08
    ä¸Ģ
    -0.08
    ï¸ı
    -0.08
    ance
    -0.08
    ä¹ĭçĶ¨
    -0.08
    ä¹ĭåĪĥ
    -0.07
    st
    -0.07
    POSITIVE LOGITS
    λάÏĩιÏĥ
    0.09
    ystems
    0.09
    æĪĸå¤ļ个
    0.08
    eparator
    0.08
    éģĹçĹĩ
    0.08
    kse
    0.08
    ÏģίοÏħ
    0.08
    నిà°ķà°¿
    0.08
    ложении
    0.08
    :date
    0.08
    Activations Density 0.056%

    No Known Activations