© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14539
    Prev
    Next
    INDEX
    Explanations

    say warm

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

    No Comments

    Negative Logits
    tokenId
    -16.88
    Curve
    -16.88
    lectic
    -16.75
    _Label
    -16.63
    labels
    -16.38
    评级
    -16.38
    csrf
    -16.13
     labels
    -16.13
    訂
    -16.00
     helmets
    -15.94
    POSITIVE LOGITS
    温
    18.63
    perature
    18.25
    关爱
    18.13
     warm
    18.00
     Warm
    17.75
    warm
    17.63
    温暖
    17.38
     Теп
    17.38
    Warm
    17.13
    关心
    17.00
    Activations Density 0.171%

    No Known Activations