© 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. 15901
    Prev
    Next
    INDEX
    Explanations

    say "non-English"

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

    No Comments

    Negative Logits
     Boone
    -21.00
    城墙
    -20.38
     Pyramid
    -18.75
     Prison
    -18.25
    (py
    -17.75
     Lö
    -17.50
    castle
    -17.50
    帐篷
    -17.38
     tomb
    -17.25
     prison
    -17.13
    POSITIVE LOGITS
    蘸
    17.25
    mailto
    17.00
    过敏
    16.63
    SPATH
    16.13
    湿润
    16.13
     Co
    15.75
    溢价
    15.63
    .digest
    15.50
     co
    15.44
    清洁
    15.00
    Activations Density 1.136%

    No Known Activations