© 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. 14036
    Prev
    Next
    INDEX
    Explanations

    say "experimental groups"

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

    No Comments

    Negative Logits
     CreateMap
    -17.63
    为客户
    -17.38
    壁垒
    -17.25
    几何
    -16.00
    _geo
    -16.00
    Geo
    -16.00
    /connect
    -15.94
    пат
    -15.75
    地理
    -15.75
     Sell
    -15.63
    POSITIVE LOGITS
     groups
    24.25
    ingroup
    23.50
     treatment
    23.50
     Group
    23.00
    Group
    23.00
     control
    23.00
    实验
    22.88
    Groups
    22.75
    控制
    22.75
     experiment
    22.63
    Activations Density 0.483%

    No Known Activations