© 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. 13955
    Prev
    Next
    INDEX
    Explanations

    say target

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

    No Comments

    Negative Logits
    连接
    -49.00
     connection
    -48.50
     connections
    -48.00
     connect
    -44.75
     connecting
    -44.75
     connects
    -44.00
    connection
    -43.00
     Connection
    -42.50
    connections
    -42.25
     Connections
    -41.75
    POSITIVE LOGITS
     target
    20.75
     targets
    19.63
    靶
    19.13
    target
    18.38
    Target
    18.25
     Target
    18.13
     Moderator
    17.00
    (target
    16.88
    购
    16.63
    ocode
    16.50
    Activations Density 1.057%

    No Known Activations