© 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. 2743
    Prev
    Next
    INDEX
    Explanations

    say dimension

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

    No Comments

    Negative Logits
    发
    -18.63
     leg
    -17.88
    Leg
    -17.75
    drs
    -17.38
     Leg
    -17.25
    leg
    -16.75
     Legends
    -16.63
    _leg
    -16.63
    -leg
    -16.00
     LEG
    -15.94
    POSITIVE LOGITS
     dimension
    80.00
     Dimension
    74.50
    Dimension
    72.00
    dimension
    69.50
     dimensions
    66.00
     dim
    65.00
    Dim
    63.75
     dimensional
    63.75
    _dimension
    63.75
    dim
    63.25
    Activations Density 0.169%

    No Known Activations