© 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. 59133
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    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
    ieg
    -0.08
    åĿıçļĦ
    -0.07
    ukti
    -0.07
    ä¸ĢåįĬ
    -0.07
    úr
    -0.07
    sis
    -0.06
    ä¹Łæĺ¯éľĢè¦ģ
    -0.06
     away
    -0.06
    atron
    -0.06
    æľīä»·åĢ¼çļĦ
    -0.06
    POSITIVE LOGITS
    getInstance
    0.08
    embed
    0.07
    cede
    0.07
    uste
    0.07
    encers
    0.07
    Instance
    0.07
    iola
    0.07
    åIJĮæĹ¥
    0.07
    çīĪ
    0.07
    NDER
    0.07
    Activations Density 0.002%

    No Known Activations