© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15085
    Prev
    Next
    INDEX
    Explanations

    say "tile"

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

    No Comments

    Negative Logits
     GAM
    -20.00
    .kr
    -17.13
     Validators
    -16.75
    _ast
    -16.63
     Bundesliga
    -16.50
    /server
    -16.50
    _FM
    -16.25
    mé
    -16.25
    jeta
    -15.75
     Мос
    -15.69
    POSITIVE LOGITS
     tile
    17.63
    Tiles
    17.25
    tile
    16.75
     tiles
    15.31
    县域
    15.25
    (tile
    14.81
    tiles
    14.56
    sites
    14.25
    	tile
    14.25
     disc
    13.88
    Activations Density 0.170%

    No Known Activations