© 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. 533
    Prev
    Next
    INDEX
    Explanations

    say silicon

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

    No Comments

    Negative Logits
    Toronto
    -22.00
     Gord
    -21.75
    加拿
    -21.25
    加拿大
    -21.00
    蓟
    -19.75
    江西省
    -19.63
     Trudeau
    -19.50
    Md
    -19.50
     Canadians
    -19.50
     Montreal
    -19.50
    POSITIVE LOGITS
     Si
    55.00
     silicon
    53.50
    Si
    53.25
    硅
    52.25
     Silicon
    49.25
     si
    45.00
    (si
    44.75
    SI
    44.00
     SI
    43.50
    _SI
    41.75
    Activations Density 0.110%

    No Known Activations