© 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. 2643
    Prev
    Next
    INDEX
    Explanations

    say "reg" words

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

    No Comments

    Negative Logits
    pot
    -20.25
     POT
    -20.13
     pot
    -20.13
     Pot
    -20.00
    Pot
    -18.13
     diff
    -17.88
    _pot
    -17.38
    eric
    -17.13
    potential
    -16.88
    (lat
    -16.75
    POSITIVE LOGITS
     reg
    48.50
     Reg
    46.75
    Reg
    46.25
    reg
    45.25
    (reg
    44.75
    	reg
    43.25
     regiment
    41.75
    -reg
    41.50
    _reg
    40.75
     REG
    40.50
    Activations Density 0.039%

    No Known Activations