© 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. 13907
    Prev
    Next
    INDEX
    Explanations

    say "transfer"

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

    No Comments

    Negative Logits
    特征
    -21.00
     targets
    -19.38
     targetType
    -19.25
    ategorized
    -19.00
    服务能力
    -17.75
     feature
    -17.63
    特性
    -17.63
    CATEGORY
    -17.38
    .toCharArray
    -17.38
     target
    -17.38
    POSITIVE LOGITS
     planes
    17.50
     transfer
    17.25
    推
    17.13
    平面
    16.63
     transmission
    16.25
     Transmit
    15.69
     transferring
    15.44
     transmit
    15.44
    cente
    15.31
    _plane
    15.25
    Activations Density 1.075%

    No Known Activations