© 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. 13994
    Prev
    Next
    INDEX
    Explanations

    say "fill"

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

    No Comments

    Negative Logits
     propertyName
    -17.75
    姓
    -17.63
    propertyName
    -17.25
     redevelopment
    -17.00
    ��
    -16.50
    unbind
    -16.50
    ARTH
    -16.25
    ayar
    -16.25
    PropertyName
    -16.00
    Syntax
    -15.75
    POSITIVE LOGITS
    液体
    31.88
     filling
    31.25
     fills
    28.88
     fill
    28.50
    填充
    28.13
     liquids
    27.50
     liquid
    27.25
    (fill
    27.00
    fill
    26.50
     filled
    26.50
    Activations Density 0.373%

    No Known Activations