© 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. 57641
    Prev
    Next
    INDEX
    Explanations

    contrasting or comparing values

    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
    ÃīG
    -0.09
     genders
    -0.08
    ikka
    -0.08
    ÐłÐ¡
    -0.08
    éĿ¢ä¸ĬçļĦ
    -0.07
    guards
    -0.07
    OfFile
    -0.07
    ä»ħæıIJä¾Ľä¿¡æģ¯
    -0.07
    åķĨä¼ļ
    -0.07
    ignano
    -0.07
    POSITIVE LOGITS
     whereas
    0.11
     Whereas
    0.08
     compare
    0.08
    缸æ¯Ķè¾ĥ
    0.07
    缸æ¯Ķä¹ĭä¸ĭ
    0.07
     ë°ĺë©´
    0.07
    èĢĮçİ°åľ¨
    0.07
     Compare
    0.07
     contrasts
    0.06
     compared
    0.06
    Activations Density 0.263%

    No Known Activations