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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16206
    Prev
    Next
    INDEX
    Explanations

    say collapse

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

    No Comments

    Negative Logits
    IRE
    -18.88
     threading
    -17.75
     thermal
    -17.75
    昱
    -17.38
    供热
    -17.13
     heaters
    -16.88
    加热
    -16.75
    (regex
    -16.63
    Regex
    -16.63
     heating
    -16.63
    POSITIVE LOGITS
    塌
    28.63
    崩溃
    25.88
     crash
    25.50
     crashing
    25.13
    倒塌
    25.00
    坍
    24.13
     collapse
    23.88
    崩
    23.25
     collapses
    22.75
     crashed
    22.38
    Activations Density 0.219%

    No Known Activations