© 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. 1570
    Prev
    Next
    INDEX
    Explanations

    say "material names"

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

    No Comments

    Negative Logits
     steel
    -51.25
     Steel
    -50.25
    Steel
    -50.00
    钢
    -47.25
    钢铁
    -44.50
    steel
    -44.00
    鋼
    -43.75
    钢材
    -41.25
    钢厂
    -35.75
    金属
    -34.00
    POSITIVE LOGITS
    ис
    13.88
    �
    13.25
    inski
    13.13
     tokenId
    13.00
    <Token
    12.75
    canvas
    12.75
    rek
    12.56
    氟
    12.44
    gos
    12.31
    口
    12.31
    Activations Density 0.070%

    No Known Activations