© 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. 2147
    Prev
    Next
    INDEX
    Explanations

    say "mirror"

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

    No Comments

    Negative Logits
    =req
    -19.00
    (req
    -16.88
    req
    -16.75
     Kro
    -16.50
     req
    -16.50
    Blo
    -15.50
     petitioner
    -15.44
    :req
    -15.44
    	req
    -15.31
    zion
    -15.25
    POSITIVE LOGITS
    镜
    88.50
     mirror
    87.50
    mirror
    83.00
    Mirror
    81.50
    鏡
    79.50
     Mirror
    79.00
     mirrors
    77.50
    镜子
    76.50
    _mirror
    69.50
     mirrored
    66.50
    Activations Density 0.132%

    No Known Activations