© 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. 2757
    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
     rev
    -18.75
     Rev
    -17.50
    rev
    -17.00
    million
    -16.75
    eric
    -16.75
    亿万
    -15.88
     милли
    -15.81
     Mill
    -15.69
    Mill
    -15.63
    cers
    -15.44
    POSITIVE LOGITS
    寄
    68.00
     register
    50.75
     registers
    49.25
    (reg
    48.25
     reg
    48.00
     Register
    47.50
    Reg
    47.50
     Reg
    47.25
    -register
    47.25
     unregister
    47.00
    Activations Density 0.040%

    No Known Activations