© 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. 37518
    Prev
    Next
    INDEX
    Explanations

    we can

    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
    еÑĤÑĭ
    -0.06
    asian
    -0.06
    еÑĤа
    -0.06
    deen
    -0.06
    ions
    -0.06
    满èħĶ
    -0.06
    羣æĥ³
    -0.06
    entifier
    -0.06
    é£ŁçļĦ
    -0.06
    kees
    -0.06
    POSITIVE LOGITS
    abouts
    0.08
    å¦ĸç²¾
    0.08
    ׼×Ķ
    0.08
    bservice
    0.08
    ondrous
    0.07
    ä¸įå¤ļ说
    0.07
    cale
    0.07
    oit
    0.07
    åŀĽ
    0.07
    szyscy
    0.07
    Activations Density 0.216%

    No Known Activations