© 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. 44710
    Prev
    Next
    INDEX
    Explanations

    celestial bodies and astronomical events

    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
     upstairs
    -0.07
    çIJĨ
    -0.07
     hypert
    -0.07
    éĵ¸
    -0.07
     weld
    -0.06
    大çIJĨçŁ³
    -0.06
    _quant
    -0.06
    ç«łé±¼
    -0.06
    ä¸Ģæĭ³
    -0.06
    ossa
    -0.06
    POSITIVE LOGITS
    人马
    0.09
    íĦ¸
    0.09
    å¸ļ
    0.08
     slur
    0.08
     ephem
    0.08
    å»ĬåĿĬå¸Ĥ
    0.08
    à¹Ģà¸Ĭ
    0.08
    å½
    0.07
    篷
    0.07
    åIJijæľ¬éĻ¢
    0.07
    Activations Density 0.004%

    No Known Activations