© 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. 6987
    Prev
    Next
    INDEX
    Explanations

    city names

    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
    åľ¨åħ¨
    -0.07
    æĺ¯æĮĩåľ¨
    -0.07
    hm
    -0.06
    ydd
    -0.06
     Chew
    -0.06
    ul
    -0.06
    yun
    -0.06
    hw
    -0.06
    etto
    -0.06
    y
    -0.06
    POSITIVE LOGITS
    elson
    0.09
    leks
    0.08
    åıijåĩº
    0.08
    Grant
    0.08
    åıijåĩºçļĦ
    0.07
    eses
    0.07
    ionalmente
    0.07
    ÛĮÙĨÙĩ
    0.07
    Wür
    0.07
    زاÙĨ
    0.07
    Activations Density 0.004%

    No Known Activations