© 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. 694
    Prev
    Next
    INDEX
    Explanations

    say Asian

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

    No Comments

    Negative Logits
    秭
    -19.75
     Newark
    -18.50
    全县
    -18.38
    该县
    -18.00
     Rutgers
    -18.00
    NJ
    -17.25
    (tf
    -17.13
    UF
    -17.00
    ód
    -16.88
    醴
    -16.88
    POSITIVE LOGITS
     Asian
    47.00
     Asia
    46.00
    亚洲
    45.50
    Asian
    43.25
    Asia
    43.25
     AS
    39.75
    东南亚
    39.50
     asia
    39.00
     Asians
    37.50
    AS
    36.75
    Activations Density 0.183%

    No Known Activations