© 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. 49170
    Prev
    Next
    INDEX
    Explanations

    guide to

    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
     ×¢×ij×ķר
    -0.08
    yaj
    -0.07
    åľ¨åĨħ
    -0.07
    gage
    -0.07
    æĹ©çŁ¥éģĵ
    -0.07
    å®¶åľ¨
    -0.07
    对äºİè¿Ļ个
    -0.06
    ãģĴ
    -0.06
     <![
    -0.06
    ÑħÑĢа
    -0.06
    POSITIVE LOGITS
     kepada
    0.24
     to
    0.24
    åĪ°ä¸Ģ个
    0.21
    åĪ°å¤§
    0.21
     Ø¥ÙĦÙĬÙĩا
    0.20
     Ø¥ÙĦÙĬÙĩ
    0.20
     Ø¥ÙĦÙī
    0.20
    åĪ°ä»ĸ
    0.19
    åĪ°çļĦ
    0.19
    åĪ°ä½ł
    0.18
    Activations Density 1.252%

    No Known Activations