© 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. 55003
    Prev
    Next
    INDEX
    Explanations

    country names

    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
    iban
    -0.07
    /play
    -0.06
    agem
    -0.06
    Tes
    -0.06
    æĺ¯ä¸Ģç§į
    -0.06
    akin
    -0.06
    ä½ľä¸ºä¸Ģç§į
    -0.06
    åĴ«å°º
    -0.06
    Ùģا
    -0.06
    ãģ¨ãģĦãģĪãģ°
    -0.06
    POSITIVE LOGITS
    女éĥİ
    0.09
    ä¸ĢäºĽå°ı
    0.08
    ABCDEFG
    0.07
    å·¥çŁ¿
    0.07
    ÅĦcz
    0.07
    _UNS
    0.07
    è¿Ļä¸ī个
    0.07
    à¹Ħมà¹Īà¸Ńย
    0.07
    å·¥åķĨä¸ļ
    0.07
    etiš
    0.07
    Activations Density 0.165%

    No Known Activations