© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44690
    Prev
    Next
    INDEX
    Explanations

    months and years

    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
    Negative Logits
    azzi
    -0.08
    æİ©
    -0.07
     SAB
    -0.07
    .Serial
    -0.07
    ằng
    -0.07
     Lau
    -0.07
    bras
    -0.07
    ứng
    -0.07
    éķľ
    -0.07
    bart
    -0.07
    POSITIVE LOGITS
    以æĿ¥çļĦ
    0.12
    以æĿ¥
    0.11
    以ä¾Ĩ
    0.10
    æĹ¥ä»¥æĿ¥
    0.09
    èĩ³ä»Ĭ
    0.09
    åݻ年
    0.08
     ÙħÙĨØ°
    0.08
     récent
    0.07
     اخÛĮر
    0.07
     earlier
    0.07
    Activations Density 0.706%

    No Known Activations