© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 1220
    Prev
    Next
    INDEX
    Explanations

    [gas] => [gas]

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

    No Comments

    Negative Logits
     gas
    -46.75
    气体
    -44.75
     Gas
    -44.00
    Gas
    -42.25
     gases
    -41.00
    gas
    -40.25
    _gas
    -40.25
     GAS
    -39.75
    气
    -34.50
    游戏
    -33.00
    POSITIVE LOGITS
    宓
    14.19
    偿
    14.13
    凤凰
    14.00
    ackson
    13.63
    archs
    13.50
     Church
    13.06
     church
    13.00
    倓
    13.00
     Tooth
    12.94
    技术创新
    12.44
    Activations Density 0.095%

    No Known Activations