© 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. 1437
    Prev
    Next
    INDEX
    Explanations

    say "float"

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

    No Comments

    Negative Logits
     Carolina
    -24.75
    Georgia
    -24.00
    东北
    -23.38
    Atlanta
    -23.25
    肝脏
    -23.13
     Georgia
    -22.75
     liver
    -22.63
    贵州
    -22.00
    Liver
    -21.38
     Liver
    -21.13
    POSITIVE LOGITS
     float
    20.63
     floating
    19.13
    (float
    17.75
    浮
    17.38
    (sym
    17.25
    float
    16.88
     Float
    16.75
     Floating
    16.63
     FLOAT
    16.63
     floated
    16.50
    Activations Density 0.133%

    No Known Activations