© 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. 15743
    Prev
    Next
    INDEX
    Explanations

    say "anger"

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

    No Comments

    Negative Logits
     Skeleton
    -18.25
    光环
    -17.75
     artwork
    -17.25
     Synopsis
    -17.25
    Skeleton
    -17.13
    艺术品
    -17.00
    摄影作品
    -16.25
     skeleton
    -16.00
    -shadow
    -16.00
     Cemetery
    -15.94
    POSITIVE LOGITS
     anger
    29.75
     angry
    28.13
    愤怒
    28.00
     rage
    26.63
    怒
    26.13
     Rage
    25.63
     angered
    24.25
    瞋
    23.88
     enraged
    23.75
     wrath
    23.38
    Activations Density 0.379%

    No Known Activations