© 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. 1030
    Prev
    Next
    INDEX
    Explanations

    Chinese stone

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

    No Comments

    Negative Logits
     stone
    -47.50
     stones
    -45.00
    石头
    -44.75
    石
    -43.00
     Stone
    -43.00
    Stone
    -42.75
     Stones
    -38.00
    石材
    -35.25
     rock
    -34.50
     rocks
    -34.50
    POSITIVE LOGITS
    阵
    15.13
    ereo
    14.00
    utto
    13.88
    di
    13.69
    国会
    13.56
    (Dialog
    13.50
    Di
    13.19
    .Tools
    13.13
    数组
    13.06
     Di
    12.94
    Activations Density 0.105%

    No Known Activations