© 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. 43536
    Prev
    Next
    INDEX
    Explanations

    Washington, Seattle, perl

    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
     Nigeria
    -0.12
     Nigerian
    -0.11
    æ¹ĺæ±Ł
    -0.09
     Django
    -0.09
     Lagos
    -0.09
     Niger
    -0.09
    æµı
    -0.09
     Jacksonville
    -0.09
    jango
    -0.08
     Python
    -0.08
    POSITIVE LOGITS
    åľ¨æĿŃå·ŀ
    0.15
    æµĻæ±Łçľģ
    0.14
    ä½ĻæĿŃ
    0.13
    æĿŃå·ŀå¸Ĥ
    0.13
    æĿŃ
    0.13
    Seattle
    0.13
     Sloven
    0.13
    诸æļ¨
    0.13
    æĿŃå·ŀ
    0.13
     Seattle
    0.12
    Activations Density 0.771%

    No Known Activations