© 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. 16120
    Prev
    Next
    INDEX
    Explanations

    say "fake" words

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

    No Comments

    Negative Logits
    Com
    -60.25
     Com
    -60.00
    -com
    -59.00
     Kom
    -57.25
     COM
    -57.25
    com
    -57.25
    COM
    -56.75
    	com
    -56.75
    _com
    -56.25
    (com
    -55.75
    POSITIVE LOGITS
    假冒
    15.38
    鳗
    14.94
    蛋糕
    14.69
    赝
    14.50
     dairy
    13.63
    伪造
    13.56
     tofu
    13.19
    走私
    13.00
    Forgery
    12.88
     ensl
    12.88
    Activations Density 4.593%

    No Known Activations