© 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. 37602
    Prev
    Next
    INDEX
    Explanations

    2 followed by parentheses or formulas

    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
    fører
    -0.09
    geld
    -0.08
    inh
    -0.08
    anness
    -0.08
    ä¼ļé¦Ĩ
    -0.07
    ekom
    -0.07
    ä¾Ŀæ³ķ追究责任
    -0.07
    cape
    -0.07
    ÙĨج
    -0.07
    orto
    -0.07
    POSITIVE LOGITS
    åĢįçļĦ
    0.09
    åıĮ
    0.08
    ,double
    0.07
    (Double
    0.07
    -thirds
    0.07
     doubles
    0.07
    èĦ¸èĽĭ
    0.07
     halves
    0.07
    éª
    0.07
    åĪĨè£Ĥ
    0.07
    Activations Density 0.049%

    No Known Activations