© 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. 16078
    Prev
    Next
    INDEX
    Explanations

    rare words

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

    No Comments

    Negative Logits
     Helsinki
    -24.75
    シリ
    -24.75
     Niagara
    -24.38
    atti
    -23.50
     Nikki
    -23.50
     Siri
    -23.38
    Ni
    -23.13
    .fi
    -22.88
    (ci
    -22.75
     Romero
    -22.13
    POSITIVE LOGITS
    藕
    19.50
     trench
    18.75
    羽毛球
    18.38
     starch
    17.75
     Wenger
    17.63
    槎
    17.50
     Ips
    17.13
    禤
    16.88
     crunch
    16.88
     rowData
    16.75
    Activations Density 3.679%

    No Known Activations