© 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. 16337
    Prev
    Next
    INDEX
    Explanations

    say "gas"

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

    No Comments

    Negative Logits
    edImage
    -19.75
    灰
    -18.25
    舵
    -17.75
     Tile
    -17.50
     ECC
    -17.25
    _GRAY
    -17.25
     Davidson
    -17.00
    理事会
    -16.88
    珊
    -16.88
     Rochester
    -16.88
    POSITIVE LOGITS
    气
    44.25
    气体
    43.50
     gas
    43.25
     gases
    38.50
    gas
    38.00
    氣
    37.25
     Gas
    36.50
    Gas
    36.25
    _gas
    36.25
    空气
    34.00
    Activations Density 0.237%

    No Known Activations