© 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. 1931
    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
    IOC
    -17.63
     IOC
    -16.13
    骑行
    -16.00
    泳
    -15.81
    轲
    -15.56
    騎
    -15.44
    wordpress
    -15.38
    骑
    -14.63
    武
    -14.56
    .setGeometry
    -14.50
    POSITIVE LOGITS
     float
    21.38
     Float
    19.25
    在美国
    18.88
    Float
    18.38
    float
    18.25
    美股
    18.13
    currency
    18.00
    浮
    18.00
     Signal
    18.00
     floating
    17.75
    Activations Density 0.404%

    No Known Activations