© 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. 1567
    Prev
    Next
    INDEX
    Explanations

    ceramic materials

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

    No Comments

    Negative Logits
    陶瓷
    -25.13
     Ceramic
    -22.38
     ceramic
    -21.13
    瓷器
    -18.50
     Palestinians
    -18.38
    地质
    -18.38
     Palestinian
    -17.88
    rame
    -17.00
    梅花
    -17.00
    贝壳
    -16.63
    POSITIVE LOGITS
     Auburn
    18.63
     movies
    18.38
     psi
    17.88
     PSI
    17.75
    psi
    17.75
    .Movie
    17.25
     bacon
    17.13
     Movies
    17.00
     dynamic
    16.88
    晏
    16.75
    Activations Density 0.246%

    No Known Activations