© 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. 44432
    Prev
    Next
    INDEX
    Explanations

    measurements followed by descriptions

    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
    ç±»çŃī
    -0.08
    uggy
    -0.08
    å¼ıåĴĮ
    -0.08
    ukai
    -0.08
    ilib
    -0.07
    ezas
    -0.07
     mens
    -0.07
    æĪĸåľ¨
    -0.07
    éĿ¢ç§¯ä¸º
    -0.07
    mens
    -0.07
    POSITIVE LOGITS
     directed
    0.07
    åĪĨå¸ĥåľ¨
    0.07
    级
    0.07
    åŃĺåľ¨äºİ
    0.07
     oriented
    0.06
    以ä¸ĬçļĦ
    0.06
    urpose
    0.06
    åĨħç»ı
    0.06
    ä½įäºİ
    0.06
    -lived
    0.06
    Activations Density 0.169%

    No Known Activations