© 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. 2799
    Prev
    Next
    INDEX
    Explanations

    say "改" words

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

    No Comments

    Negative Logits
    facility
    -18.75
    Fac
    -18.38
    ˆ
    -18.25
     facility
    -17.75
    Vec
    -17.25
    (serial
    -17.00
     Vec
    -16.75
    icc
    -16.38
     Deserialize
    -16.25
    <Vec
    -16.13
    POSITIVE LOGITS
    改
    53.75
     modifier
    33.50
     modification
    31.25
     modifiers
    30.88
     modified
    30.75
     Modifier
    30.38
     modify
    29.38
     mod
    28.75
     Modification
    28.63
     modifies
    28.50
    Activations Density 0.061%

    No Known Activations