© 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
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1108
    Prev
    Next
    INDEX
    Explanations

    [carb] => [carburetor]

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

    No Comments

    Negative Logits
     Carson
    -20.25
     Fishing
    -19.00
    脱发
    -18.88
     plantation
    -18.50
    -anchor
    -18.50
    捕鱼
    -18.25
    staking
    -18.13
    anchors
    -18.00
    estate
    -18.00
    neys
    -18.00
    POSITIVE LOGITS
    电子
    12.25
    .Qual
    12.25
    Po
    12.19
     WB
    12.19
    纸质
    12.00
    mat
    11.94
    ln
    11.81
    MAT
    11.69
     WINDOWS
    11.56
    pcm
    11.56
    Activations Density 0.036%

    No Known Activations