© 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. 2498
    Prev
    Next
    INDEX
    Explanations

    say 倍

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

    No Comments

    Negative Logits
    retain
    -18.50
    reflection
    -18.13
    Registry
    -18.00
    ret
    -17.88
    	ref
    -17.38
    reg
    -17.38
     tech
    -17.25
    丝
    -17.25
    -ref
    -16.88
    策略
    -16.88
    POSITIVE LOGITS
     rep
    28.13
    倍
    27.88
    (rep
    25.75
    Rep
    25.13
    	rep
    23.63
     Rep
    23.50
    乘
    22.75
    rep
    21.75
     replication
    20.88
     multip
    20.50
    Activations Density 0.054%

    No Known Activations