© 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. 1690
    Prev
    Next
    INDEX
    Explanations

    say "triangle"

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

    No Comments

    Negative Logits
     Russia
    -42.75
     Russians
    -41.75
    俄罗斯
    -41.00
     Russian
    -40.75
    Russian
    -40.25
    Russia
    -39.00
    俄国
    -38.50
     russe
    -38.00
    俄军
    -33.25
    俄
    -33.00
    POSITIVE LOGITS
     triangle
    19.75
    Triangle
    18.38
    JKLM
    17.38
     cartridge
    17.13
    三角
    17.00
     Triangle
    16.50
     ABC
    16.38
    ABC
    16.00
    triangle
    15.69
     sdf
    15.13
    Activations Density 0.316%

    No Known Activations