© 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. 16045
    Prev
    Next
    INDEX
    Explanations

    say Unicode

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

    No Comments

    Negative Logits
    pol
    -24.13
    jq
    -23.00
     jq
    -22.63
    (jq
    -21.75
     cJSON
    -21.75
    -pol
    -21.38
    POL
    -21.25
    Pol
    -21.25
     pol
    -21.13
     Pol
    -21.00
    POSITIVE LOGITS
    鹫
    20.38
    开封
    19.50
     Lucifer
    19.38
    庆典
    19.25
    firefox
    18.88
    景德
    18.50
    香菇
    18.38
    庆祝
    18.25
    bookmark
    17.88
     Glory
    17.75
    Activations Density 4.787%

    No Known Activations