© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 530
    Prev
    Next
    INDEX
    Explanations

    say "Jewish"

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

    No Comments

    Negative Logits
    耒
    -19.63
     ARM
    -18.38
     TX
    -18.38
     �
    -18.13
    �
    -18.13
    ల
    -17.88
    衡阳
    -17.75
     Texas
    -17.75
     RX
    -17.13
     Tx
    -16.88
    POSITIVE LOGITS
     Jewish
    51.00
     Jews
    49.25
     Jew
    46.25
     Judaism
    42.75
     jewish
    42.50
     Rabbi
    38.25
    犹
    37.25
     synagogue
    35.50
     Juda
    33.50
     JS
    33.25
    Activations Density 0.214%

    No Known Activations