© 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. 2747
    Prev
    Next
    INDEX
    Explanations

    say 精

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

    No Comments

    Negative Logits
    segment
    -17.38
    pir
    -17.25
    段
    -17.13
    Beth
    -16.38
    otten
    -16.25
     segment
    -16.25
     Mem
    -16.25
     Beth
    -16.25
     Reply
    -15.94
     retVal
    -15.88
    POSITIVE LOGITS
    精
    59.75
    ref
    36.50
     Ref
    35.50
    	ref
    35.50
     ref
    34.50
    Ref
    32.50
    (ref
    31.88
     refinement
    31.88
     refin
    31.50
    .ref
    31.38
    Activations Density 0.139%

    No Known Activations