© 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. 598
    Prev
    Next
    INDEX
    Explanations

    align with business goals

    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
    稿件æĿ¥æºIJ
    -0.08
    ivals
    -0.08
    çĽ¸å¯¹èĢĮè¨Ģ
    -0.07
    ä¸Ģ个æĸ°
    -0.07
    hto
    -0.07
    ialis
    -0.07
    åıĤä¸İåħ¶ä¸Ń
    -0.07
    atia
    -0.07
    Ñĩина
    -0.07
    алÑĮ
    -0.07
    POSITIVE LOGITS
    ing
    0.09
     zamanda
    0.08
     concept
    0.08
    ä¸įäºĨ
    0.07
    à¸ģัà¸ļà¸ģาร
    0.07
    bewert
    0.07
    añ
    0.07
    çij¾
    0.07
    å¾Ĺå¾Ī好
    0.07
    aan
    0.07
    Activations Density 0.006%

    No Known Activations