© 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. 54945
    Prev
    Next
    INDEX
    Explanations

    improvement / improves / improving / diabetic

    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
     tartal
    -0.08
    ebra
    -0.07
    ajari
    -0.07
     Barbosa
    -0.07
     garde
    -0.07
    (Enum
    -0.07
     betrayed
    -0.07
    andle
    -0.07
    linger
    -0.07
    arters
    -0.07
    POSITIVE LOGITS
    æĶ¹åĸĦ
    0.15
    æĶ¹åĸĦäºĨ
    0.14
    åı¯ä»¥æĶ¹åĸĦ
    0.12
     improvement
    0.12
     Improvement
    0.12
    æĺİæĺ¾æĶ¹åĸĦ
    0.12
    åĴĮæĶ¹åĸĦ
    0.11
     improves
    0.11
     improving
    0.11
     improve
    0.11
    Activations Density 0.388%

    No Known Activations