© 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. 16245
    Prev
    Next
    INDEX
    Explanations

    say "ab"

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

    No Comments

    Negative Logits
    韶
    -20.00
    槐
    -20.00
    潇
    -19.88
     Clint
    -18.88
    绿城
    -18.38
    飓
    -18.25
     Trent
    -18.00
    醌
    -17.38
    黑龙
    -17.38
     Gree
    -17.25
    POSITIVE LOGITS
     Kab
    43.50
    (rb
    42.25
    rab
    42.00
    	rb
    41.50
    аб
    40.00
    (tb
    39.75
    rb
    39.50
     rb
    39.50
     Rab
    39.00
     Cab
    38.75
    Activations Density 7.330%

    No Known Activations