© 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. 1788
    Prev
    Next
    INDEX
    Explanations

    say "angle"

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

    No Comments

    Negative Logits
     chess
    -18.50
     Lawson
    -18.38
    HeaderText
    -17.75
    围棋
    -16.88
    SSH
    -16.50
     Einstein
    -16.25
     Eigen
    -16.13
     eigen
    -16.00
     Alps
    -16.00
    弈
    -15.50
    POSITIVE LOGITS
     angular
    21.88
     Angular
    21.25
    ENG
    21.00
    angular
    20.88
    Angle
    20.00
    θ
    20.00
     angle
    19.88
    angle
    19.88
     ang
    19.75
     angel
    19.75
    Activations Density 0.324%

    No Known Activations