© 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. 64114
    Prev
    Next
    INDEX
    Explanations

    unexpected or surprising

    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
    èĤ¯å®ļæĺ¯
    -0.07
     firmly
    -0.06
    utte
    -0.06
     securely
    -0.06
    PRETTY
    -0.06
     essentials
    -0.06
    èĤ¯å®ļä¼ļ
    -0.06
    มัà¹Īà¸Ļà¸Ħà¸ĩ
    -0.06
    hti
    -0.06
     smoothly
    -0.06
    POSITIVE LOGITS
     surprising
    0.13
    å·§åIJĪ
    0.13
    ç«Ł
    0.13
    æĦıæĥ³ä¸įåĪ°çļĦ
    0.13
     surprisingly
    0.12
    ç«ŁçĦ¶æĺ¯
    0.12
     unexpected
    0.12
    ç«ŁçĦ¶
    0.12
    åĩºä¹İ
    0.12
     surprise
    0.11
    Activations Density 0.045%

    No Known Activations