© 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. 16083
    Prev
    Next
    INDEX
    Explanations

    principles

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

    No Comments

    Negative Logits
    .TAG
    -17.88
    tat
    -17.63
    <tag
    -17.50
    TAG
    -16.75
    TRS
    -15.81
    飞
    -15.75
    websocket
    -15.75
    飛
    -15.56
    (sq
    -15.13
    _sq
    -15.00
    POSITIVE LOGITS
    guid
    17.50
     voice
    16.13
     nucleus
    15.94
    核
    15.81
     guid
    15.75
    指南
    15.38
     bone
    15.31
    簪
    15.25
     voices
    15.25
    勺
    15.19
    Activations Density 0.190%

    No Known Activations