© 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. 16311
    Prev
    Next
    INDEX
    Explanations

    say "lock"

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

    No Comments

    Negative Logits
    .swagger
    -15.19
    asca
    -15.19
    ▿
    -14.81
    Ε
    -14.63
    药材
    -14.56
     Vega
    -14.56
     ска
    -14.19
    簌
    -14.13
    科教
    -14.13
    substr
    -14.13
    POSITIVE LOGITS
    locks
    36.25
    lock
    36.00
     lock
    36.00
    Lock
    34.75
     locks
    34.25
    LOCK
    33.00
     Lock
    33.00
    _lock
    32.50
    -lock
    32.25
     locking
    32.00
    Activations Density 0.118%

    No Known Activations