© 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. 52172
    Prev
    Next
    INDEX
    Explanations

    waste and loss

    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
    umon
    -0.08
    é¦ĸä¾ĭ
    -0.07
    å®ŀæĹ¶æĽ´æĸ°
    -0.07
    ä¸ĢèĪ¬äºº
    -0.07
    åĨĪ
    -0.07
    bron
    -0.07
    -Man
    -0.07
    /vendors
    -0.07
    ernels
    -0.07
    åĪ°æĿ¥
    -0.06
    POSITIVE LOGITS
    浪费
    0.17
     wast
    0.17
     wasted
    0.16
     ineff
    0.16
     unnecessarily
    0.15
     waste
    0.14
     losses
    0.14
    浪费äºĨ
    0.14
     inefficient
    0.14
    æįŁèĢĹ
    0.14
    Activations Density 0.109%

    No Known Activations