© 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. 38245
    Prev
    Next
    INDEX
    Explanations

    surprisingly, ironically, strangely, oddly enough

    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
     باÙĦتأÙĥÙĬد
    -0.09
    èĤ¯å®ļè¦ģ
    -0.09
    æĹłçĸij
    -0.08
    èĤ¯å®ļæĺ¯
    -0.08
    à¹ģà¸Ļà¹Īà¸Ļà¸Ńà¸Ļ
    -0.08
     sicuramente
    -0.08
     Obviously
    -0.08
     obviously
    -0.08
    èĩªçĦ¶æĺ¯
    -0.08
    Obviously
    -0.08
    POSITIVE LOGITS
    ç«ŁçĦ¶
    0.21
    å±ħçĦ¶
    0.21
    ç«ŁçĦ¶æĺ¯
    0.18
    ç«Ł
    0.18
    å±ħçĦ¶æĺ¯
    0.17
    ç«Łæĺ¯
    0.16
    ä»ĸç«ŁçĦ¶
    0.15
     surprisingly
    0.13
    åıįèĢĮ
    0.12
    åıįåĢĴ
    0.11
    Activations Density 0.470%

    No Known Activations