© 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. 15851
    Prev
    Next
    INDEX
    Explanations

    Secretary of

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

    No Comments

    Negative Logits
    clid
    -19.13
    clud
    -18.00
    trand
    -17.25
    illé
    -16.13
    NTAX
    -16.13
    旻
    -15.50
     Fram
    -15.31
    idy
    -15.25
    框架
    -15.19
    模板
    -15.19
    POSITIVE LOGITS
    /min
    21.00
    Interior
    20.88
    /Internal
    20.75
    Min
    20.63
     Interior
    20.00
     interior
    19.75
     min
    19.63
    -min
    19.50
     Exterior
    19.50
     internal
    19.38
    Activations Density 0.107%

    No Known Activations