© 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. 57561
    Prev
    Next
    INDEX
    Explanations

    surprise or surprised when

    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
    olean
    -0.09
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    -0.08
    oves
    -0.08
     seperate
    -0.08
    aphore
    -0.08
    ulaire
    -0.08
    inage
    -0.08
    ä¸Ģä½ĵçļĦ
    -0.08
    åĴ³åĴ³
    -0.08
    ulare
    -0.08
    POSITIVE LOGITS
    ingly
    0.12
     surprise
    0.10
    æĦıå¤ĸ
    0.10
    æĦıæĸĻ
    0.10
    æĦıå¤ĸçļĦ
    0.10
    æĥĬåĸľ
    0.09
     unexpected
    0.09
     sorpresa
    0.09
     surprising
    0.09
     surprised
    0.09
    Activations Density 0.162%

    No Known Activations