© 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. 1805
    Prev
    Next
    INDEX
    Explanations

    say script

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

    No Comments

    Negative Logits
    河北
    -25.38
    橡胶
    -23.00
    σ
    -22.75
     σ
    -22.50
    河北省
    -22.13
    (uuid
    -21.38
    京津冀
    -20.75
     rubber
    -20.25
    sigma
    -19.88
     sigma
    -19.00
    POSITIVE LOGITS
     scripts
    28.25
    Scripts
    27.75
     Scripts
    27.38
     script
    27.00
     scripting
    24.88
    scripts
    24.75
    脚
    24.75
    Script
    23.75
    script
    23.63
    _script
    23.63
    Activations Density 0.259%

    No Known Activations