© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14191
    Prev
    Next
    INDEX
    Explanations

    say "archives"

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

    No Comments

    Negative Logits
    .setOutput
    -15.94
    DEV
    -15.69
    モデル
    -15.63
    路口
    -15.44
     gioc
    -15.13
    設計
    -15.13
    游戏中
    -14.69
     desenv
    -14.63
    模特
    -14.63
     Spieler
    -14.44
    POSITIVE LOGITS
    档案
    34.25
     archives
    33.75
     Archives
    33.50
     archive
    30.25
    archives
    29.38
     collections
    28.50
     archival
    27.88
     Archive
    27.50
     library
    27.13
     Library
    27.00
    Activations Density 0.663%

    No Known Activations