© 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. 1426
    Prev
    Next
    INDEX
    Explanations

    say ax

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

    No Comments

    Negative Logits
     hotels
    -41.25
    酒店
    -41.00
     hotel
    -39.00
     Hotel
    -34.25
     Hotels
    -33.00
    ホテル
    -33.00
    Hotel
    -31.50
    大酒店
    -30.00
    hotel
    -29.75
     호텔
    -27.25
    POSITIVE LOGITS
    /rc
    17.50
    瑜
    17.13
    _ax
    17.13
    鲁迅
    16.50
    Axes
    16.38
    Axis
    16.25
    .ax
    16.00
    语言
    15.81
    axe
    15.56
     pys
    15.50
    Activations Density 0.038%

    No Known Activations