© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 47196
    Prev
    Next
    INDEX
    Explanations

    contribution and efficiency

    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
    åĽ¢
    -0.08
    åĽ¢çļĦ
    -0.08
    åľĺ
    -0.08
    红éħĴ
    -0.07
    親åŃIJ
    -0.07
    asser
    -0.07
    emens
    -0.07
    reff
    -0.07
     ultimately
    -0.07
    _DEV
    -0.07
    POSITIVE LOGITS
    è´¡çĮ®
    0.09
    ran
    0.08
     contributes
    0.08
    åįķçĭ¬
    0.07
    çļĦè´¡çĮ®
    0.07
    -contrib
    0.07
    è²¢çį»
    0.07
     Contribution
    0.07
    èİİ
    0.07
    é³ĸ
    0.07
    Activations Density 0.069%

    No Known Activations