© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14245
    Prev
    Next
    INDEX
    Explanations

    say "parameter"

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

    No Comments

    Negative Logits
    控制
    -30.50
     Control
    -29.38
     control
    -29.13
     CONTROL
    -27.13
    -control
    -27.13
    control
    -26.88
    _control
    -26.00
     控
    -25.25
    CONTROL
    -25.25
    Control
    -24.88
    POSITIVE LOGITS
     parameter
    21.38
    参数
    20.50
     parameters
    20.13
    _param
    18.75
    parameters
    18.13
     dimensions
    18.00
    parameter
    18.00
     Parameter
    17.38
    Param
    17.13
    -parameter
    17.00
    Activations Density 2.076%

    No Known Activations