© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 2
    Prev
    Next
    INDEX
    Explanations

    say DC

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

    No Comments

    Negative Logits
    阿根廷
    -18.50
     Sergio
    -18.00
     Sloven
    -17.75
     Slovenia
    -17.75
     LSU
    -17.63
    溇
    -17.38
    梅西
    -17.25
     Gujarat
    -17.25
    阆
    -17.25
    坭
    -17.13
    POSITIVE LOGITS
     DC
    75.50
    DC
    65.50
     dc
    64.00
    (dc
    62.00
    _dc
    58.25
    dc
    57.75
    京
    57.25
    _DC
    57.25
    /dc
    54.00
     Washington
    53.25
    Activations Density 0.146%

    No Known Activations