© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17974
    Prev
    Next
    INDEX
    Explanations

    players acting in games

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ئÙĩ
    -0.06
     Mancha
    -0.05
    abet
    -0.05
     pär
    -0.05
     educated
    -0.05
    pen
    -0.05
    boa
    -0.05
     figures
    -0.05
    åIJ¸åıĸ
    -0.05
    loth
    -0.05
    POSITIVE LOGITS
    ãĤĤãģĹãĤį
    0.06
     Inser
    0.06
    æĦıæĢĿ表示
    0.06
    лева
    0.06
    åĴĮå¤ĦçIJĨ
    0.05
    ussen
    0.05
     ngôi
    0.05
    åīįä¸Ģ
    0.05
    wer
    0.05
    ãģķãģ¾
    0.05
    Activations Density 0.005%

    No Known Activations