© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 13936
    Prev
    Next
    INDEX
    Explanations

    say "punishment"

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

    No Comments

    Negative Logits
    崛
    -20.63
    预测
    -18.25
     FEATURES
    -17.25
    heroes
    -17.25
    .analytics
    -17.13
     analytics
    -16.88
     Lump
    -16.63
    特质
    -16.38
    predict
    -16.25
    analytics
    -16.25
    POSITIVE LOGITS
    罚
    41.50
     punishment
    39.50
     punishments
    38.00
    罚款
    37.50
    处罚
    37.00
    罰
    36.00
     penalties
    36.00
    惩罚
    35.75
     penalty
    34.25
     punish
    32.75
    Activations Density 0.644%

    No Known Activations