© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15536
    Prev
    Next
    INDEX
    Explanations

    say praise

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

    No Comments

    Negative Logits
    冶
    -19.88
    ToolStrip
    -19.63
     Knife
    -19.50
    Knife
    -19.38
    ipl
    -18.25
    渔船
    -17.88
    setItem
    -17.75
    刀
    -17.75
    ItemCount
    -17.63
    NavItem
    -17.25
    POSITIVE LOGITS
     praise
    31.38
     praising
    30.38
     praises
    28.88
    赞美
    28.63
    颂
    28.25
     celebrating
    28.00
    庆祝
    27.38
    赞
    27.25
     celebration
    26.88
     celebrate
    26.25
    Activations Density 0.355%

    No Known Activations