© 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. 58906
    Prev
    Next
    INDEX
    Explanations

    unemployment rate

    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
    æĸĩæĺİåįķä½į
    -0.08
    åĨħéĥ¨å®¡è®¡
    -0.08
    åIJĿåķ¬
    -0.07
    ิà¸ķิ
    -0.07
    ÙĨدÙĩ
    -0.07
    篡
    -0.07
    riminator
    -0.07
     spol
    -0.07
    moid
    -0.07
    åįĩåįİ
    -0.07
    POSITIVE LOGITS
     unemployment
    0.14
    失ä¸ļ
    0.13
    失ä¸ļçİĩ
    0.12
     unemployed
    0.11
    失æ¥Ń
    0.11
    å°±ä¸ļ
    0.10
    æ±ĤèģĮ
    0.10
    æī¾å·¥ä½ľ
    0.10
    employment
    0.09
    å°±ä¸ļçİĩ
    0.09
    Activations Density 0.057%

    No Known Activations