© 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. 16359
    Prev
    Next
    INDEX
    Explanations

    say peace

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

    No Comments

    Negative Logits
    金融科技
    -19.13
    焰
    -18.50
    珥
    -18.25
    izr
    -17.63
    RIPT
    -17.38
    蒂
    -17.25
     fingert
    -17.13
     ResourceType
    -17.00
    挡
    -17.00
    ECTOR
    -16.88
    POSITIVE LOGITS
    peace
    21.25
     Peace
    20.13
    sigma
    19.25
    Peace
    18.88
     peace
    18.75
    σ
    18.25
     sigma
    18.13
     σ
    17.50
    SS
    17.00
    和平
    17.00
    Activations Density 0.068%

    No Known Activations