© 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. 34603
    Prev
    Next
    INDEX
    Explanations

    negation or contrast

    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
     appunto
    -0.08
    èĢĮéĿŀ
    -0.08
     not
    -0.08
    èĢĮä¸įè§ģ
    -0.07
    ä¸įåĨįæĺ¯
    -0.07
    èĢĮä¸įæĺ¯
    -0.07
    ä¸įä»ħæľī
    -0.07
    ä¸įä¸Ģå®ļæĺ¯
    -0.07
    ä¸įä½ıçļĦ
    -0.07
    ä¸įä»ħæĺ¯
    -0.07
    POSITIVE LOGITS
     nor
    0.14
     anymore
    0.12
    มาà¸ģà¸Ļัà¸ģ
    0.12
    èĢĮæĺ¯è¦ģ
    0.11
     melainkan
    0.11
    æĽ´ä¸įä¼ļ
    0.11
    èĢĮæĺ¯åĽłä¸º
    0.11
    èĢĮæĺ¯
    0.11
     sondern
    0.10
    æĽ´ä¸įèĥ½
    0.10
    Activations Density 0.123%

    No Known Activations