© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15492
    Prev
    Next
    INDEX
    Explanations

    say "salt"

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

    No Comments

    Negative Logits
    (Vertex
    -17.50
     Capcom
    -17.00
    家长们
    -16.88
    顶
    -16.75
     getParent
    -16.50
     Ferrari
    -16.38
    蜘蛛
    -16.25
     Beetle
    -16.13
    妩
    -16.00
    谷爱凌
    -15.94
    POSITIVE LOGITS
     salt
    59.00
    盐
    57.50
    salt
    53.75
     Salt
    52.25
    鹽
    52.00
    Salt
    51.50
     salts
    48.75
    _salt
    47.75
     salty
    46.75
     sal
    45.75
    Activations Density 0.230%

    No Known Activations