© 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. 15678
    Prev
    Next
    INDEX
    Explanations

    say "thread"

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

    No Comments

    Negative Logits
    .Footer
    -20.25
     Ike
    -18.38
     Feinstein
    -17.00
    <footer
    -15.75
     Signed
    -15.44
    FieldType
    -15.38
     Hust
    -15.25
     trí
    -15.25
    amous
    -15.19
    巡视
    -15.13
    POSITIVE LOGITS
     thread
    42.75
     Thread
    40.25
    Thread
    40.00
     threads
    39.75
    thread
    39.75
    	thread
    38.00
     threading
    36.00
    /thread
    35.75
    -thread
    35.75
    _thread
    35.75
    Activations Density 0.173%

    No Known Activations