© 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. 11920
    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
    ren
    -0.07
     maxim
    -0.07
     تعÙħ
    -0.07
    /
    -0.06
    kl
    -0.06
     den
    -0.06
    éĢŀ
    -0.06
     ú
    -0.06
    éľĦ
    -0.06
    çIJª
    -0.06
    POSITIVE LOGITS
    bsp
    0.09
    empa
    0.08
    abat
    0.08
    æĸĩåĮĸä¸İ
    0.08
    -nil
    0.08
    á»Ļp
    0.08
     Maggi
    0.08
    меÑĤе
    0.08
    acam
    0.07
    æ¯Ķåݻ年åIJĮæľŁ
    0.07
    Activations Density 0.000%

    No Known Activations