© 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. 38530
    Prev
    Next
    INDEX
    Explanations

    mathematical operations with numbers

    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
    imat
    -0.08
    nellement
    -0.07
    coming
    -0.07
    master
    -0.07
    itarian
    -0.07
    trash
    -0.07
    agers
    -0.07
    à¦ŀà§įà¦ļ
    -0.07
     behalf
    -0.07
    lessly
    -0.07
    POSITIVE LOGITS
    ä¹ĭ为
    0.07
    æ³ŀ
    0.07
    ç¿¡
    0.07
    ubro
    0.07
    夫æĸ¯åŁº
    0.07
    çŁ£
    0.07
    åĩ¿
    0.06
    ä¸įäºĨ
    0.06
    ãģ£ãģ¨
    0.06
    ×Ļף
    0.06
    Activations Density 0.057%

    No Known Activations