© 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. 44612
    Prev
    Next
    INDEX
    Explanations

    Interchangeable lens, Link, stage, membrane, transistor, particles, emission, tender

    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
    /rest
    -0.08
    enerator
    -0.08
    imizer
    -0.08
    ndo
    -0.07
    yles
    -0.07
    cape
    -0.07
    aren
    -0.07
    embr
    -0.07
    onces
    -0.07
    ouw
    -0.07
    POSITIVE LOGITS
    å¼ı
    0.17
    -based
    0.16
    åŀĭ
    0.16
    -Based
    0.13
    åŀĭ人æīį
    0.12
    åŀĭçļĦ
    0.11
    å¼ıçļĦ
    0.11
    å¼ı为
    0.11
    åŀĭåĴĮ
    0.11
    å¼ıãģ®
    0.11
    Activations Density 1.273%

    No Known Activations