© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14121
    Prev
    Next
    INDEX
    Explanations

    say "enter"

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

    No Comments

    Negative Logits
     setFrame
    -19.38
    -setting
    -19.13
     connections
    -19.13
     Connections
    -18.88
     connection
    -18.00
    /connection
    -17.50
    setError
    -17.13
    connection
    -17.00
     setting
    -16.88
    setting
    -16.88
    POSITIVE LOGITS
    转入
    28.25
    转
    26.38
    进入
    25.75
     enters
    24.50
     enter
    24.38
     entered
    24.25
    轉
    24.00
    进入了
    24.00
     entering
    23.75
    进
    23.38
    Activations Density 0.907%

    No Known Activations