© 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. 37671
    Prev
    Next
    INDEX
    Explanations

    professor or works for

    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°ij女
    -0.07
    åľ¨å¿ĥä¸Ń
    -0.07
    appen
    -0.07
    adians
    -0.07
    ilha
    -0.07
    åľ¨è¡ĮåĬ¨
    -0.07
    常å§Ķä¼ļ
    -0.07
    æīĢæľª
    -0.06
    ä¸įèIJ½
    -0.06
    eniu
    -0.06
    POSITIVE LOGITS
    æĭħä»»
    0.10
     duties
    0.10
    dut
    0.09
     должноÑģÑĤи
    0.09
    æķĻäºİ
    0.08
    à¸ķำà¹ģหà¸Ļà¹Īà¸ĩ
    0.08
    äºĮ线
    0.08
    èģĮ称
    0.08
     presso
    0.08
     serve
    0.08
    Activations Density 0.542%

    No Known Activations