© 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. 15981
    Prev
    Next
    INDEX
    Explanations

    say capture

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

    No Comments

    Negative Logits
     pz
    -18.63
    邮轮
    -18.25
     Hornets
    -18.13
    タイ
    -18.13
     BLL
    -17.75
    _dtype
    -17.50
    pll
    -17.00
     Zombie
    -17.00
    姚明
    -17.00
     Swarm
    -16.88
    POSITIVE LOGITS
    capture
    23.75
     capture
    23.13
    .capture
    21.88
    Capt
    20.75
     captures
    20.50
     capturing
    20.13
     captured
    20.00
     Capt
    19.50
     Capture
    19.50
    覆盖面
    19.38
    Activations Density 0.310%

    No Known Activations