© 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. 16188
    Prev
    Next
    INDEX
    Explanations

    say 强

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

    No Comments

    Negative Logits
    锦绣
    -17.50
    獭
    -17.00
    jal
    -17.00
     prophecy
    -15.63
    绸
    -15.38
     silky
    -15.25
     prol
    -15.13
    apro
    -15.06
     silk
    -14.63
    請求
    -14.50
    POSITIVE LOGITS
    强
    35.50
     strong
    30.88
     stronger
    29.63
    strong
    29.50
    更强
    29.25
     Strong
    29.00
     strongest
    29.00
     weaker
    28.50
    Strong
    28.13
    最强
    28.00
    Activations Density 0.180%

    No Known Activations