© 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. 31325
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and equations

    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
    ä½ıæĪ¿åŁİ乡建设
    -0.07
    æ§Ľ
    -0.07
     Fol
    -0.07
    менов
    -0.06
    ÙIJس
    -0.06
    —I
    -0.06
    fle
    -0.06
     depend
    -0.06
    _DOT
    -0.06
    bum
    -0.06
    POSITIVE LOGITS
    িà¦ķা
    0.08
    _pdata
    0.08
    è¦ģ被
    0.07
    æĬĬä¸Ģ个
    0.07
    owan
    0.07
    orem
    0.07
    érance
    0.07
    ÙĬرÙĬ
    0.07
    åı¯ä»¥æĬĬ
    0.07
    ç»Ŀåľ°
    0.07
    Activations Density 0.008%

    No Known Activations