© 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. 2816
    Prev
    Next
    INDEX
    Explanations

    say 汤

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

    No Comments

    Negative Logits
    ret
    -22.00
     Ret
    -19.88
    _ret
    -19.13
     ret
    -18.63
    Ret
    -18.38
    (ret
    -17.38
    .ret
    -16.88
     RET
    -16.50
    	ret
    -16.38
     retina
    -16.38
    POSITIVE LOGITS
    汤
    68.50
    湯
    57.25
     therm
    40.25
     Ther
    39.75
     therapy
    38.50
    ther
    38.25
     Therm
    35.50
     ther
    35.25
     Therapy
    35.25
    therapy
    31.25
    Activations Density 0.047%

    No Known Activations