© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1888
    Prev
    Next
    INDEX
    Explanations

    do not say hydrogen

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

    No Comments

    Negative Logits
    氢
    -37.75
     hydrogen
    -37.75
    氢能
    -26.00
     Hydro
    -20.75
    荷花
    -18.25
    ationToken
    -17.38
    hydro
    -17.13
    燃料电池
    -16.38
    免疫
    -16.00
    婆
    -15.69
    POSITIVE LOGITS
    镖
    22.88
    /screen
    18.50
    影片
    18.38
    电影
    17.00
    .screen
    16.50
     screens
    16.25
    Screen
    16.13
     movie
    15.94
     screen
    15.88
     engineering
    15.88
    Activations Density 0.077%

    No Known Activations