© 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. 2939
    Prev
    Next
    INDEX
    Explanations

    say lat

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

    No Comments

    Negative Logits
    彭
    -23.38
    .Prop
    -19.38
     proposition
    -19.13
    .prop
    -19.00
     Proposition
    -17.88
    _prop
    -17.75
     Penny
    -17.63
    prop
    -16.63
    Prop
    -16.63
    (prop
    -16.13
    POSITIVE LOGITS
     Lat
    70.00
    Lat
    68.00
     lat
    64.50
    (lat
    62.25
    lat
    60.25
    .lat
    56.75
    _lat
    56.75
    -lat
    54.75
    ,lat
    53.00
     LAT
    51.75
    Activations Density 0.083%

    No Known Activations