© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1283
    Prev
    Next
    INDEX
    Explanations

    say "play"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    经济
    -67.50
     economic
    -60.75
     Economic
    -59.75
    經濟
    -59.75
     economy
    -55.50
     economics
    -52.75
    economic
    -52.25
     Economy
    -50.25
    -economic
    -48.75
    经济发展
    -48.25
    POSITIVE LOGITS
    oplay
    15.88
    -play
    15.38
     play
    15.25
    PasswordField
    15.00
    (play
    14.38
     MART
    14.31
    Play
    14.31
     Mart
    13.94
    .Fields
    13.94
    uba
    13.88
    Activations Density 0.393%

    No Known Activations