© 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. 15940
    Prev
    Next
    INDEX
    Explanations

    say hue/saturation

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

    No Comments

    Negative Logits
     curse
    -20.00
    -router
    -18.63
     Curse
    -18.25
    自理
    -18.25
    _clock
    -17.63
    .Sql
    -17.63
     clk
    -17.63
     sticker
    -17.50
    clock
    -17.13
     Cork
    -16.88
    POSITIVE LOGITS
     saturation
    19.38
    饱和
    17.75
    补
    17.00
     satur
    16.25
     complement
    16.25
     hue
    16.13
    调
    15.88
     grad
    15.81
     Hue
    15.56
    補
    15.56
    Activations Density 0.165%

    No Known Activations