© 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. 14112
    Prev
    Next
    INDEX
    Explanations

    say old

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

    No Comments

    Negative Logits
    位置
    -25.13
    的位置
    -24.63
    计算
    -23.63
     position
    -23.00
     Positions
    -21.88
     getLocation
    -21.63
    osition
    -21.50
     positions
    -21.38
     computation
    -21.38
     Position
    -21.25
    POSITIVE LOGITS
     transfer
    17.63
    转移
    16.75
     Transfer
    16.63
     transferred
    16.38
    .Transfer
    16.13
    transfer
    15.63
     transferring
    15.50
     class
    15.19
     conduct
    15.06
    -transfer
    15.06
    Activations Density 0.865%

    No Known Activations