© 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. 48943
    Prev
    Next
    INDEX
    Explanations

    digit or number sequences

    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
     sust
    -0.08
    amore
    -0.08
     verge
    -0.08
    ankind
    -0.07
    imat
    -0.07
    æģį
    -0.07
    ç¥Ŀç¦ıä½ł
    -0.07
     /^(
    -0.07
    åīįåįĬ
    -0.07
     solid
    -0.06
    POSITIVE LOGITS
    lott
    0.07
    æĺ¯æľĢ大çļĦ
    0.07
    nop
    0.07
    acock
    0.07
    ä¸Ģå®ļä¸įèĥ½
    0.07
    è¿ŀçĿĢ
    0.06
    åįļæĸĩ
    0.06
    äºĮè¿ŀ
    0.06
     neither
    0.06
     intermedi
    0.06
    Activations Density 0.011%

    No Known Activations