© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3275
    Prev
    Next
    INDEX
    Explanations

    say "train"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    隐私
    -19.25
    …↵↵↵
    -18.88
    …↵↵↵↵
    -18.75
    行为
    -18.25
    组
    -18.13
    的行为
    -17.75
    数组
    -17.63
    ...↵↵↵↵
    -17.38
    ...↵↵↵↵↵↵
    -17.25
     antibiotic
    -16.75
    POSITIVE LOGITS
     Train
    22.75
     train
    22.25
    Train
    18.63
     trains
    18.38
    列车
    18.00
    train
    17.88
     derail
    17.75
     road
    17.25
    _train
    17.13
     pipe
    17.13
    Activations Density 0.010%

    No Known Activations