© 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. 16288
    Prev
    Next
    INDEX
    Explanations

    say containers

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

    No Comments

    Negative Logits
    .mysql
    -21.38
     Rohingya
    -21.00
     immunity
    -20.50
    免疫
    -20.38
     Immigration
    -20.38
    MYSQL
    -19.25
     anonymity
    -19.25
     Mormons
    -19.13
    imity
    -18.88
     immun
    -18.63
    POSITIVE LOGITS
    壶
    23.00
     basket
    21.75
    匣
    21.25
    架
    21.13
    iram
    20.13
     erect
    19.63
    箕
    19.63
     bundle
    19.63
    斛
    19.50
    筐
    19.00
    Activations Density 1.605%

    No Known Activations