© 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. 44259
    Prev
    Next
    INDEX
    Explanations

    yoga and meditation

    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
    çĹħæŃ»
    -0.08
     Machinery
    -0.07
    æĬ¢çľ¼
    -0.07
    è·Ľ
    -0.07
    ä¸į缺
    -0.07
    éĩįç»Ħ
    -0.07
    ç¾ģ
    -0.07
    ardt
    -0.07
    .define
    -0.07
     brutto
    -0.07
    POSITIVE LOGITS
     meditation
    0.13
    åĨ¥æĥ³
    0.12
     Meditation
    0.12
     mindfulness
    0.11
     relaxation
    0.11
     calming
    0.10
    åĶ¤éĨĴ
    0.10
     yoga
    0.10
    æĶ¾æĿ¾
    0.09
     soothing
    0.09
    Activations Density 0.093%

    No Known Activations