© 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. 21635
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Ø´ÛĮ
    -0.07
    atsby
    -0.07
     Sce
    -0.07
    éĩĪ
    -0.07
    اÙĨÛĮ
    -0.07
    ocator
    -0.07
    enstr
    -0.07
     Sér
    -0.07
    çļĦæµ·æ´ĭ
    -0.07
    ãĥĩãĥ¼ãĤ¿ãĥĻãĥ¼ãĤ¹
    -0.07
    POSITIVE LOGITS
    ç¡®
    0.07
    aub
    0.07
    aday
    0.07
    åĴĮç²¾ç¥ŀ
    0.07
    é¡¿
    0.07
    bord
    0.06
    é¢ij
    0.06
    è¾ħæĸĻ
    0.06
    ä¸ļåĬ¡ç´łè´¨
    0.06
    å¡
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.