© 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. 15600
    Prev
    Next
    INDEX
    Explanations

    say enemies

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

    No Comments

    Negative Logits
     Analyzer
    -17.25
    (Channel
    -16.50
    _Delay
    -15.88
     lắng
    -15.63
    .Binding
    -15.31
    兑现
    -15.31
     Channel
    -15.25
    _echo
    -15.06
    Binder
    -15.00
    服务区
    -14.69
    POSITIVE LOGITS
    入侵
    22.00
    侵略
    20.88
     invaders
    20.50
    侵
    17.88
     enemy
    17.75
     threats
    17.63
     enc
    17.63
    enemy
    17.50
    敌人
    17.50
    Enemy
    17.13
    Activations Density 0.232%

    No Known Activations