© 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. 2244
    Prev
    Next
    INDEX
    Explanations

    say emp words

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

    No Comments

    Negative Logits
    结算
    -17.25
    pot
    -16.50
    -reset
    -15.56
     pot
    -15.44
     settlement
    -15.31
     Settlement
    -15.25
     Annotation
    -15.19
    kel
    -15.19
    Quote
    -14.94
     registr
    -14.88
    POSITIVE LOGITS
     Emp
    67.50
     empirical
    65.50
    Emp
    63.75
    emp
    63.25
     empir
    57.75
    许
    55.50
     em
    55.00
     emp
    54.75
    (emp
    54.25
    em
    47.00
    Activations Density 0.058%

    No Known Activations