© 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. 451
    Prev
    Next
    INDEX
    Explanations

    say Greek and Arabic

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

    No Comments

    Negative Logits
    TS
    -19.13
     Olsen
    -18.00
    	ts
    -18.00
     ts
    -17.88
    洛杉矶
    -17.75
     Bruins
    -17.63
    PA
    -17.50
    ts
    -17.38
    Ts
    -17.25
    rozen
    -16.75
    POSITIVE LOGITS
    希腊
    19.13
    阿拉伯
    18.75
    oise
    16.88
    Greek
    16.63
    erne
    16.50
     Arist
    16.25
    叙利亚
    16.25
     Greek
    16.25
    (sql
    15.88
     Arabic
    15.88
    Activations Density 0.183%

    No Known Activations