© 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. 2857
    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
    vant
    -17.00
    seg
    -16.88
    (seg
    -15.94
     seg
    -15.69
    シーン
    -15.06
    ethyl
    -14.56
     SEG
    -14.56
    酒业
    -14.44
    乙
    -14.38
    公益活动
    -14.19
    POSITIVE LOGITS
     Rep
    57.75
    Rep
    54.25
    (rep
    52.75
     rep
    52.00
     Republic
    52.00
     REP
    50.00
    Republic
    49.50
    	rep
    48.00
     republic
    48.00
    rep
    48.00
    Activations Density 0.092%

    No Known Activations