© 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. 14125
    Prev
    Next
    INDEX
    Explanations

    arithmetic operators and assignment

    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
    èĢĮä¸Ķæĺ¯
    -0.08
    ==='
    -0.08
    ä¹Łåı¯èĥ½æĺ¯
    -0.07
    èĢĮå¼ķèµ·
    -0.07
    å°±æĿ¥
    -0.07
    upes
    -0.07
    ä¸ĢæīĢ
    -0.07
    èĢĮåıĪ
    -0.07
    ä¹Łåı¯ä»¥æĺ¯
    -0.07
    æĪij们就æĿ¥
    -0.07
    POSITIVE LOGITS
    pace
    0.08
     would
    0.07
     =
    0.07
    geg
    0.07
    íļĮëĬĶ
    0.07
    åd
    0.07
    اء
    0.07
    forEach
    0.07
    geschlossen
    0.07
    ditor
    0.07
    Activations Density 0.015%

    No Known Activations