© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 686
    Prev
    Next
    INDEX
    Explanations

    Shakespeare play

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

    No Comments

    Negative Logits
    _BUCKET
    -20.63
    萝
    -19.25
    ള
    -19.13
     Batter
    -18.88
    /aws
    -18.13
     getEmail
    -17.75
    AES
    -17.75
    efs
    -17.75
    瘰
    -17.75
     Crypt
    -17.50
    POSITIVE LOGITS
    张家界
    22.25
     Ty
    21.00
    湘西
    20.25
    Ty
    19.75
     Nepal
    19.00
     NSA
    18.13
    株洲
    17.25
     Ib
    17.13
    (ib
    17.00
    澧
    16.88
    Activations Density 0.037%

    No Known Activations