© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18678
    Prev
    Next
    INDEX
    Explanations

    is or are followed by punctuation

    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
    注æĦıçļĦæĺ¯
    -0.09
     ...)
    -0.09
    ãģªãģ®ãģ¯
    -0.09
    ”âĢ¦
    -0.09
    _defs
    -0.08
    illion
    -0.08
    odar
    -0.08
    olino
    -0.08
     !**
    -0.08
     ìĿĺíķľ
    -0.08
    POSITIVE LOGITS
    .
    0.09
    樣çļĦ
    0.08
    ,
    0.07
    :
    0.07
    s
    0.06
    èĢĮåIJĮ
    0.06
    ;
    0.06
    æł·åŃIJ
    0.06
     kind
    0.06
    _.
    0.06
    Activations Density 0.002%

    No Known Activations