© 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. 2462
    Prev
    Next
    INDEX
    Explanations

    say "效"

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

    No Comments

    Negative Logits
    条
    -17.63
    记
    -17.63
    _reserved
    -16.75
    居
    -16.25
     resin
    -15.75
    й
    -15.63
    _registered
    -15.56
    _RES
    -15.44
    記
    -15.44
    vro
    -15.31
    POSITIVE LOGITS
     ref
    26.13
    效
    24.88
     Eq
    24.63
     eq
    24.00
     def
    24.00
    	ref
    22.75
    Eq
    22.38
     Ref
    21.75
    .ref
    21.38
    ref
    20.25
    Activations Density 0.065%

    No Known Activations