© 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. 44768
    Prev
    Next
    INDEX
    Explanations

    remains/remain + descriptor

    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
    gether
    -0.10
    wards
    -0.08
    ting
    -0.08
    onomic
    -0.08
    bidden
    -0.08
    anom
    -0.07
    apl
    -0.07
    γÏĮ
    -0.07
    æł·çļĦ
    -0.07
    ddy
    -0.07
    POSITIVE LOGITS
    antly
    0.11
    lah
    0.09
    ãģªãĤīãģļ
    0.09
    ÑħодиÑĤе
    0.08
    emente
    0.08
    ات
    0.08
    بات
    0.08
    ently
    0.08
    erge
    0.08
    ingham
    0.08
    Activations Density 0.037%

    No Known Activations