© 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. 7077
    Prev
    Next
    INDEX
    Explanations

    movie titles and directors

    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
     postura
    -0.06
    书ä¸Ĭ
    -0.06
    ä¹IJäºİ
    -0.06
    èģĮå·¥çļĦ
    -0.06
    å¼ıä¸Ń
    -0.06
    λεÏħ
    -0.06
     denom
    -0.06
    orni
    -0.06
     passé
    -0.05
    èĩªåĬ¨æĮ¡
    -0.05
    POSITIVE LOGITS
    aman
    0.08
     izle
    0.08
    ouc
    0.08
    èĬ±ä¸Ģ
    0.08
    æĬ¥ä»ĩ
    0.07
     cÃŃm
    0.07
    prest
    0.07
    çķĶ
    0.07
    éĢĨæµģ
    0.07
    ampf
    0.07
    Activations Density 0.046%

    No Known Activations