© 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. 1047
    Prev
    Next
    INDEX
    Explanations

    glass

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

    No Comments

    Negative Logits
    玻璃
    -56.00
     glass
    -51.25
    Glass
    -50.00
     Glass
    -46.75
    glass
    -46.25
     glasses
    -40.25
     Glasses
    -37.25
     Glas
    -32.25
    玻
    -32.00
    璃
    -28.75
    POSITIVE LOGITS
     Ryder
    14.31
    缘
    14.00
    �
    13.81
    .Qt
    13.63
     Nut
    13.63
    菏
    13.44
     UIT
    13.38
     Harper
    12.88
    dto
    12.81
    ullets
    12.81
    Activations Density 0.060%

    No Known Activations