© 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. 7278
    Prev
    Next
    INDEX
    Explanations

    "ation" suffixes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    essin
    -0.07
     trav
    -0.07
     rit
    -0.07
    åĨĴ
    -0.06
    TEL
    -0.06
    è¦ģè¿Ľè¡Į
    -0.06
    yser
    -0.06
     Rub
    -0.06
    ÑĩаÑĤки
    -0.06
    tel
    -0.06
    POSITIVE LOGITS
    å½¢æĪIJçļĦ
    0.11
    åĪĽå»ºäºĨ
    0.11
     creates
    0.10
     membentuk
    0.10
    åĪĽéĢłåĩº
    0.10
     forming
    0.10
     menghasilkan
    0.10
     creating
    0.10
     produces
    0.10
    creates
    0.10
    Activations Density 0.807%

    No Known Activations