© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3011
    Prev
    Next
    INDEX
    Explanations

    say 减

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

    No Comments

    Negative Logits
     TERMIN
    -21.38
     termin
    -20.75
     mirrored
    -20.50
     reflected
    -19.75
     Serial
    -19.63
     reflection
    -19.38
    .Serial
    -19.13
    镜子
    -19.13
    (serial
    -19.00
    Mirror
    -19.00
    POSITIVE LOGITS
    Cond
    20.00
    减
    19.38
    eting
    19.38
     rel
    18.88
     Cond
    18.25
    .cond
    17.13
    .rel
    16.88
    改
    16.75
    (cond
    16.50
    Min
    16.13
    Activations Density 0.062%

    No Known Activations