© 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. 15865
    Prev
    Next
    INDEX
    Explanations

    say humor

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

    No Comments

    Negative Logits
     Sign
    -17.13
     sign
    -16.63
    缔
    -16.50
    (sign
    -16.25
    password
    -15.94
    (password
    -15.88
    密码
    -15.88
    .Sign
    -15.81
    .ssl
    -15.63
     cov
    -15.38
    POSITIVE LOGITS
     joke
    40.75
     comedy
    40.25
     laughter
    39.50
    幽默
    39.00
     jokes
    38.75
    笑
    38.50
     humorous
    37.50
     humor
    37.00
     laugh
    36.50
     comedic
    36.25
    Activations Density 0.479%

    No Known Activations