© 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. 26709
    Prev
    Next
    INDEX
    Explanations

    technical concepts and definitions

    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
     (?
    -0.08
    åIJİèĢħ
    -0.07
    çļĦè¯Ħä»·æĺ¯
    -0.07
    OfMonth
    -0.07
    å°½æľī
    -0.07
     (?)
    -0.07
    äºĨä¸Ģæł·
    -0.07
    мом
    -0.07
     respectively
    -0.07
     <--
    -0.07
    POSITIVE LOGITS
    ares
    0.09
    using
    0.08
    é¦ĸåħĪ
    0.07
    <![
    0.07
     Berk
    0.07
    :&
    0.07
     using
    0.07
    家ä½ı
    0.07
    ãĢĤãĢĮ
    0.07
    overe
    0.07
    Activations Density 0.015%

    No Known Activations