© 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. 59772
    Prev
    Next
    INDEX
    Explanations

    place names and 'within'

    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
    grab
    -0.08
    guer
    -0.08
    fram
    -0.07
    .Extension
    -0.07
    -0.07
     Principle
    -0.06
    rawer
    -0.06
    dued
    -0.06
    gh
    -0.06
     Allgeme
    -0.06
    POSITIVE LOGITS
    emps
    0.08
    æĵº
    0.08
    oskop
    0.07
    塵
    0.07
    å°ĺ
    0.07
    åIJįæĢĿ
    0.07
    æĨ¬
    0.07
    漸
    0.07
    isset
    0.07
    associate
    0.07
    Activations Density 0.001%

    No Known Activations