© 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. 16324
    Prev
    Next
    INDEX
    Explanations

    say "sacrifice"

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

    No Comments

    Negative Logits
     Clarkson
    -20.00
    メニュー
    -18.38
    mouseout
    -17.63
    ологии
    -17.25
     Catalyst
    -17.13
    usiness
    -17.00
    Interop
    -16.63
    mdp
    -16.50
    OOM
    -16.50
    akers
    -16.50
    POSITIVE LOGITS
     martyr
    20.88
    殉
    20.75
    牺牲
    20.50
     sacrifices
    19.88
     heroic
    19.63
    def
    19.50
     Sacr
    19.00
     sacrifice
    18.63
    hero
    18.63
     marty
    18.50
    Activations Density 0.364%

    No Known Activations