© 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. 1202
    Prev
    Next
    INDEX
    Explanations

    say "ball"

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

    No Comments

    Negative Logits
     WATER
    -28.38
     water
    -28.38
    Water
    -27.50
    water
    -27.25
     Water
    -27.00
    水域
    -26.63
    _water
    -26.13
    -water
    -25.25
     Wasser
    -25.13
    水上
    -24.63
    POSITIVE LOGITS
    球
    18.13
    inus
    17.88
    ball
    17.13
     ball
    17.00
     Roman
    16.63
    .ball
    16.13
    Ball
    15.94
     Ball
    15.81
     balls
    15.25
    𝜙
    15.19
    Activations Density 0.316%

    No Known Activations