© 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. 51982
    Prev
    Next
    INDEX
    Explanations

    phrases following "on"

    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
    ä¸ĢçĤ¹åĦ¿
    -0.11
    ãģķãģ¾ãģĸãģ¾ãģª
    -0.10
     afterward
    -0.09
     zufolge
    -0.09
    æħ¢æħ¢åľ°
    -0.08
    é©Ń
    -0.08
     nond
    -0.08
    ãģľãģ²
    -0.08
    æľīçĤ¹åĦ¿
    -0.08
    prese
    -0.08
    POSITIVE LOGITS
     Whilst
    0.12
    Whilst
    0.12
    åģļ为
    0.12
     whilst
    0.11
    Lets
    0.10
    综åIJĪçĹĩ
    0.10
     seperate
    0.09
     insure
    0.09
     amongst
    0.09
     ë¶ĢíĦ°
    0.08
    Activations Density 2.684%

    No Known Activations