© 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. 56822
    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
    太éĥİ
    -0.08
    utherland
    -0.08
    keer
    -0.08
    amer
    -0.07
    è¿Ļ群
    -0.07
     bã
    -0.07
    egy
    -0.07
    ç«ĭ足
    -0.07
    ürf
    -0.07
    .rx
    -0.07
    POSITIVE LOGITS
    毫
    0.07
    Ł
    0.06
     shim
    0.06
    ç®Ń
    0.06
    [](
    0.06
    ä¸įåĪ°çļĦ
    0.06
    é¢Ħç¥Ŀ
    0.06
    èĢĮçĶŁ
    0.06
     geop
    0.06
    éĩijæŃ£
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.