© 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. 2160
    Prev
    Next
    INDEX
    Explanations

    say register

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

    No Comments

    Negative Logits
    morph
    -18.00
    rev
    -16.00
     Morph
    -15.63
     morph
    -15.44
    agus
    -14.94
    渗
    -14.88
     morphology
    -14.88
    rer
    -14.44
    owered
    -14.38
     REV
    -14.19
    POSITIVE LOGITS
    注册
    90.00
     register
    82.50
     registration
    79.50
     registers
    77.50
     Register
    77.50
     registrations
    76.00
     registered
    75.50
    register
    75.50
     Registration
    74.50
    (register
    74.00
    Activations Density 0.283%

    No Known Activations