© 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. 2938
    Prev
    Next
    INDEX
    Explanations

    say Beth

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

    No Comments

    Negative Logits
    .em
    -20.88
    -em
    -19.63
     Em
    -19.50
     em
    -19.13
    'em
    -19.00
    	em
    -18.38
    (em
    -17.75
    许
    -17.38
    Em
    -17.13
     EM
    -16.75
    POSITIVE LOGITS
    乙
    71.00
    甲
    67.00
     Beth
    64.50
    Beth
    60.00
    丙
    57.50
     meth
    53.25
     Meth
    53.00
    meth
    49.75
    eth
    47.75
     Eth
    47.50
    Activations Density 0.028%

    No Known Activations