© 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. 2667
    Prev
    Next
    INDEX
    Explanations

    say "rep"

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

    No Comments

    Negative Logits
    乙
    -15.75
    roup
    -15.06
     philosophical
    -15.00
     Eth
    -14.81
    erge
    -14.81
    kea
    -14.69
    civil
    -14.56
    文明
    -14.50
     ethical
    -14.38
    .AP
    -14.13
    POSITIVE LOGITS
     rep
    95.00
    Rep
    89.50
     Rep
    89.00
    (rep
    88.00
    rep
    87.50
    	rep
    79.50
    .rep
    77.00
    _rep
    74.50
     REP
    69.00
    REP
    63.50
    Activations Density 0.299%

    No Known Activations