© 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. 34972
    Prev
    Next
    INDEX
    Explanations

    piano playing

    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
    èµĬ
    -0.08
    azaar
    -0.08
    gaz
    -0.07
    åIJ¹åĵį
    -0.07
    æĭĶæ²³
    -0.07
    éĹ¯çº¢çģ¯
    -0.07
     containers
    -0.07
    azel
    -0.07
     gaze
    -0.07
    è·Łè¸ª
    -0.07
    POSITIVE LOGITS
     phÃŃm
    0.10
    éĶ®çĽĺ
    0.10
     keyboard
    0.09
     piano
    0.09
     клави
    0.09
     Piano
    0.09
    keyboard
    0.08
    Keyboard
    0.08
    éĴ¢çIJ´
    0.08
    aida
    0.08
    Activations Density 0.067%

    No Known Activations