© 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. 59020
    Prev
    Next
    INDEX
    Explanations

    magnetic resonance imaging

    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
    aec
    -0.09
     Aé
    -0.08
    otype
    -0.08
    è§Ĵè´¨
    -0.08
    itzen
    -0.07
    ê¹ĥ
    -0.07
     hawk
    -0.07
    pread
    -0.07
    åѵåĮĸ
    -0.07
    iffs
    -0.07
    POSITIVE LOGITS
     MRI
    0.10
    ç£ģåħ±æĮ¯
    0.09
     imaging
    0.09
     magnetic
    0.09
    MRI
    0.09
     magnet
    0.09
     Magnetic
    0.08
     brain
    0.08
    ç£ģ
    0.08
     magnets
    0.08
    Activations Density 0.067%

    No Known Activations