© 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. 2536
    Prev
    Next
    INDEX
    Explanations

    say "sent" words

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

    No Comments

    Negative Logits
    (protocol
    -17.75
    Protocol
    -16.63
    proto
    -16.00
     Perr
    -16.00
    _protocol
    -15.88
     proto
    -15.81
    [dim
    -15.75
    Proto
    -15.56
     protocol
    -15.31
     protocols
    -15.31
    POSITIVE LOGITS
     Sent
    51.25
    Sent
    48.50
    sent
    48.00
    .sent
    46.00
    (sent
    44.75
    _sent
    43.75
     sen
    43.00
     SENT
    41.00
     sent
    40.75
    Sen
    40.75
    Activations Density 0.053%

    No Known Activations