© 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. 59965
    Prev
    Next
    INDEX
    Explanations

    words ending in -able, -ive, -ous, -ent, -al, -y

    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
    undy
    -0.08
     gesta
    -0.07
    ito
    -0.07
    avin
    -0.07
    arat
    -0.06
    зо
    -0.06
    é¡ĺ
    -0.06
    ä¸įå°±æĺ¯
    -0.06
    irth
    -0.06
    Ùħا
    -0.06
    POSITIVE LOGITS
    liy
    0.07
    WithOptions
    0.07
    离
    0.07
    ç¨ĭ度ä¸Ĭ
    0.06
    lys
    0.06
    Cop
    0.06
    ddf
    0.06
    ÑħаÑħ
    0.06
    æĥ³æĸ¹
    0.06
    ogenesis
    0.06
    Activations Density 0.001%

    No Known Activations