© 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. 37760
    Prev
    Next
    INDEX
    Explanations

    winter Olympics

    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
    Not in Any Lists

    No Comments

    Negative Logits
    mate
    -0.07
    è¿Ľä¸ĢæŃ¥ä¼ĺåĮĸ
    -0.07
    å¸Ĥåľºä»·
    -0.07
    ева
    -0.06
     realtime
    -0.06
     excell
    -0.06
    åı°ä¸Ĭ
    -0.06
    err
    -0.06
    è¿ĽéĢĢ
    -0.06
    线ä¸Ĭ线ä¸ĭ
    -0.06
    POSITIVE LOGITS
    å½ĵæŶçļĦ
    0.17
    åIJİæĿ¥çļĦ
    0.16
    åľ¨å½ĵæŶ
    0.16
    å½ĵæŶ
    0.15
    later
    0.14
    åIJİæĿ¥
    0.13
     later
    0.13
    çķ¶æĻĤ
    0.13
    éĽıå½¢
    0.13
     damals
    0.13
    Activations Density 0.717%

    No Known Activations