© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22820
    Prev
    Next
    INDEX
    Explanations

    passive voice constructions

    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
    é§Ħ
    -0.08
    ÅĤoÅĽÄĩ
    -0.08
    èµ
    -0.08
    åľ¨ä¸º
    -0.07
    å·¡è§Ĩåijĺ
    -0.07
    bons
    -0.07
    æı®
    -0.07
    profil
    -0.07
    åľ¨è´Ńä¹°
    -0.07
    è¿Ļæĸ¹éĿ¢çļĦ
    -0.07
    POSITIVE LOGITS
    被åĬ¨
    0.09
    æĺ¯è¢«
    0.08
     passive
    0.08
    å·¥åºı
    0.08
     imperson
    0.08
    åĴĮ被
    0.08
     agency
    0.08
    çļĦ被
    0.08
    å¤ļæĸ¹
    0.08
    é¢łåĢĴ
    0.07
    Activations Density 0.004%

    No Known Activations