© 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. 24099
    Prev
    Next
    INDEX
    Explanations

    email addresses and names

    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
    ãĤĤãģ®ãģ®
    -0.07
    ÙĦد
    -0.06
    ukkan
    -0.06
    ÑĢиÑĤ
    -0.06
    ä¸ĢåıĮ
    -0.06
    osaur
    -0.06
    ä¸Ģ对
    -0.06
    ÙĨز
    -0.06
    ernos
    -0.06
    ieder
    -0.06
    POSITIVE LOGITS
    éĥ¨ç½²
    0.08
    çļĦæīĭä¸Ń
    0.07
    ä¾Ŀæ³ķé¡»ç»ı
    0.07
    ë¶Ģìŀ¥
    0.07
    åŃļ
    0.07
    ç¥ŀä¹ĭ
    0.07
    гоÑĢе
    0.07
    ãĥĵãĥĥãĤ¯
    0.06
    ber
    0.06
    ylan
    0.06
    Activations Density 0.006%

    No Known Activations