© 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. 644
    Prev
    Next
    INDEX
    Explanations

    European countries and institutions

    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
    iman
    -0.08
     tampil
    -0.08
    ÙĩراÙĨ
    -0.08
    yson
    -0.08
    -NLS
    -0.08
    BigInt
    -0.08
    ahari
    -0.08
    ogie
    -0.08
    ادÙħ
    -0.08
    yder
    -0.08
    POSITIVE LOGITS
    ish
    0.07
    artz
    0.06
    红æĺŁ
    0.06
     https
    0.06
    illes
    0.06
    auer
    0.06
    azz
    0.06
    ury
    0.06
    ago
    0.06
     revis
    0.06
    Activations Density 0.031%

    No Known Activations