© 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. 59875
    Prev
    Next
    INDEX
    Explanations

    common word endings like "esta" and "sted"

    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
    paru
    -0.07
    é¾Ħ
    -0.06
    åľ¨ä¸Ģ个
    -0.06
    urez
    -0.06
    ucch
    -0.06
    IAL
    -0.06
    æŃ¤èµ·å½¼ä¼ı
    -0.06
    åĩĮåİī
    -0.06
    drv
    -0.06
    _increment
    -0.06
    POSITIVE LOGITS
    esta
    0.08
    åĴĮè¦ģæ±Ĥ
    0.08
    èijĨ
    0.08
    stead
    0.07
    etty
    0.07
    åľ¨åħĪ
    0.07
    rish
    0.07
    ÖĦ
    0.07
    éal
    0.07
    sted
    0.07
    Activations Density 0.001%

    No Known Activations