© 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. 14292
    Prev
    Next
    INDEX
    Explanations

    say "position" words

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

    No Comments

    Negative Logits
    syntax
    -16.88
    ProductId
    -16.75
    鬘
    -16.63
    决战
    -16.25
    trand
    -16.13
    productId
    -16.00
    框架
    -15.88
    _syntax
    -15.44
     Formats
    -15.31
    PLAN
    -15.13
    POSITIVE LOGITS
    岗位
    24.50
     posts
    24.38
    岗
    23.38
     position
    23.25
     Title
    23.00
     Posts
    22.50
    position
    22.38
    职位
    22.38
    职务
    22.00
     post
    21.75
    Activations Density 0.452%

    No Known Activations