© 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. 44716
    Prev
    Next
    INDEX
    Explanations

    WEARIED or Limerick

    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
    esia
    -0.08
    -base
    -0.07
    istas
    -0.07
    æĸĩç«łæłĩçŃ¾
    -0.07
    egas
    -0.07
     Jaw
    -0.07
    jaw
    -0.07
    å¾Ĺä¸į
    -0.07
    pheres
    -0.07
     Salv
    -0.06
    POSITIVE LOGITS
    ioc
    0.08
    aré
    0.07
    SZ
    0.07
    æ²IJ
    0.07
    æĢ»ç®Ĺ
    0.07
    çĶ¨æĪ·æıIJä¾Ľ
    0.06
     Savo
    0.06
    byt
    0.06
    ász
    0.06
    æĺ¯ä¸Ģ家éĽĨ
    0.06
    Activations Density 0.091%

    No Known Activations