© 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. 15794
    Prev
    Next
    INDEX
    Explanations

    say "land features"

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

    No Comments

    Negative Logits
     aquatic
    -23.38
    γ
    -22.50
     flooding
    -22.38
    游
    -22.38
    旅馆
    -21.63
    银河
    -21.63
     floated
    -21.50
     Noah
    -21.50
     Liverpool
    -21.38
     Flood
    -21.38
    POSITIVE LOGITS
    墩
    23.63
    坂
    23.00
    札
    22.88
    冈
    22.13
     Ridge
    22.00
     Jade
    21.63
    笋
    21.25
    帖
    21.00
     ridge
    20.88
    bolt
    20.63
    Activations Density 6.611%

    No Known Activations