© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15402
    Prev
    Next
    INDEX
    Explanations

    say "dark" words

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

    No Comments

    Negative Logits
    鲤
    -18.75
    flation
    -17.88
    ице
    -16.88
     Inflate
    -16.50
     pBuffer
    -16.38
    祓
    -16.38
    装配式
    -16.13
     ieee
    -16.13
    自理
    -16.13
     Cit
    -16.00
    POSITIVE LOGITS
     dark
    44.50
     Dark
    41.50
    黑
    41.00
    黑色
    40.75
    dark
    39.25
    Dark
    39.00
     darker
    38.25
     black
    38.00
     darkness
    37.75
     DARK
    37.50
    Activations Density 0.212%

    No Known Activations