© 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. 40066
    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
    inet
    -0.06
     Scha
    -0.06
    è¦ģ注æĦıçļĦæĺ¯
    -0.06
    indu
    -0.06
     rep
    -0.06
    .fs
    -0.06
    ä¸Ĭçľĭ
    -0.06
     somehow
    -0.06
    ä½Ĩæĺ¯ä½ł
    -0.06
     Cint
    -0.06
    POSITIVE LOGITS
    è¯ĿæĿ¥
    0.09
    kiye
    0.08
    kson
    0.08
    ovy
    0.07
    ÙĬرÙĬ
    0.07
    olini
    0.07
    éļĶå¤ľ
    0.07
     Neves
    0.07
     unm
    0.07
    uya
    0.07
    Activations Density 0.000%

    No Known Activations