© 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. 4905
    Prev
    Next
    INDEX
    Explanations

    figures and tables

    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
    çĽĬ
    -0.08
    æĭįæĭį
    -0.07
    æĬ±
    -0.07
    ÙĤات
    -0.06
    ities
    -0.06
    okit
    -0.06
    ä¸įæ¼ı
    -0.06
    ä¸Ģéģĵ
    -0.06
    ç¨
    -0.06
    oke
    -0.06
    POSITIVE LOGITS
    åīį款
    0.08
     -:
    0.07
    åѦåı²
    0.07
    dependence
    0.07
    çĪ±èĩªå·±
    0.07
    SEN
    0.07
    .—
    0.07
    为åģļ好
    0.07
    Ø¡
    0.07
     ÙħÛĮÙĦ
    0.07
    Activations Density 0.005%

    No Known Activations