© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15545
    Prev
    Next
    INDEX
    Explanations

    say "Y" words

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

    No Comments

    Negative Logits
    娄
    -17.75
    排骨
    -16.25
    azen
    -15.81
    箪
    -14.88
     Glouce
    -14.81
    rances
    -14.63
    摭
    -14.25
    楝
    -13.75
    郗
    -13.69
    莼
    -13.69
    POSITIVE LOGITS
     SY
    46.50
    sy
    45.50
    SY
    45.00
     PY
    45.00
    PY
    44.75
     sy
    44.75
     Sy
    43.75
    .sy
    43.75
    Sy
    43.25
     CY
    42.75
    Activations Density 6.670%

    No Known Activations