© 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. 626
    Prev
    Next
    INDEX
    Explanations

    adverbs of certainty and emphasis

    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
    åīĶ
    -0.07
     ÙħØŃا
    -0.07
    osso
    -0.07
    åIJĪ
    -0.06
    itemid
    -0.06
    ãĤĦãģ£ãģ¨
    -0.06
    ×Ļר×ķת
    -0.06
    éĢ
    -0.06
    oller
    -0.06
    uty
    -0.06
    POSITIVE LOGITS
    ç¡®å®ŀæĺ¯
    0.18
    ç¡®å®ŀ
    0.18
    ä¹Łç¡®å®ŀ
    0.17
    ç¡®æľī
    0.16
     indeed
    0.16
    çļĦç¡®æĺ¯
    0.16
    確實
    0.15
    çļĦç¡®
    0.15
    ç¡®
    0.13
    Indeed
    0.13
    Activations Density 0.177%

    No Known Activations