© 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. 15670
    Prev
    Next
    INDEX
    Explanations

    say ing

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

    No Comments

    Negative Logits
     Bracket
    -19.25
    挂牌
    -19.00
    握手
    -18.88
     cage
    -18.88
     bracket
    -18.38
    钥匙
    -18.38
     handshake
    -17.50
     synonym
    -17.50
    assel
    -17.25
    牵手
    -17.25
    POSITIVE LOGITS
     MSP
    21.63
    受灾
    21.63
     Disaster
    19.75
    灾
    19.63
     disasters
    18.63
     Spokane
    18.50
    acz
    18.38
    陕
    17.75
     Spam
    17.00
     SP
    16.88
    Activations Density 1.491%

    No Known Activations