© 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. 14661
    Prev
    Next
    INDEX
    Explanations

    say "weight units"

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

    No Comments

    Negative Logits
    Subsystem
    -18.13
    帘
    -17.88
    ERV
    -17.50
    ERA
    -17.50
    麋
    -17.13
    aho
    -16.25
    iera
    -16.13
    ảo
    -15.56
     subsystem
    -15.50
    .Extension
    -15.38
    POSITIVE LOGITS
    weights
    19.25
    weight
    18.63
     weight
    17.88
     weights
    17.50
    ounces
    16.88
    Weights
    16.63
     ounces
    16.50
    体重
    16.38
     Weight
    16.25
    ounce
    15.69
    Activations Density 0.043%

    No Known Activations