© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3223
    Prev
    Next
    INDEX
    Explanations

    say "DI"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    市教育局
    -14.69
    暗
    -14.44
    的语言
    -14.25
    市教育
    -14.13
     Event
    -13.94
    étr
    -13.69
    éc
    -13.44
    总收入
    -13.31
    墅
    -13.25
    节
    -13.13
    POSITIVE LOGITS
    DI
    17.25
    在玩家
    17.13
    Diagram
    15.88
    asti
    15.75
    particles
    15.56
    /ui
    15.13
    particle
    14.88
    websocket
    14.88
    player
    14.69
     DI
    14.69
    Activations Density 0.015%

    No Known Activations