© 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. 2858
    Prev
    Next
    INDEX
    Explanations

    say metric

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

    No Comments

    Negative Logits
     tet
    -17.00
    鞘
    -16.88
     net
    -16.50
     nets
    -16.13
    宝
    -15.88
    net
    -15.50
    龛
    -15.06
    网
    -15.00
    terr
    -14.94
    tet
    -14.56
    POSITIVE LOGITS
    计量
    53.00
    Metric
    43.00
     Meter
    43.00
     Metric
    42.75
     metric
    42.75
     meter
    41.75
    metric
    41.00
     metrics
    39.75
    Meter
    39.75
    _metric
    38.00
    Activations Density 0.039%

    No Known Activations