© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1487
    Prev
    Next
    INDEX
    Explanations

    say "anti"

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

    No Comments

    Negative Logits
    氧化
    -33.50
     oxidation
    -33.00
     Ox
    -32.75
    AX
    -30.63
     ax
    -30.00
    ax
    -29.75
     oxidative
    -29.63
    oxid
    -29.38
    _AX
    -28.38
    _ax
    -28.38
    POSITIVE LOGITS
    军
    16.00
    棉
    15.63
     military
    13.94
     Britain
    13.75
    軍
    13.63
     UK
    13.50
    币
    13.38
    лот
    13.38
    スマ
    13.31
     Lam
    13.19
    Activations Density 0.069%

    No Known Activations