© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15868
    Prev
    Next
    INDEX
    Explanations

    say gear

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    estic
    -18.75
    预售
    -17.50
    焰
    -17.38
    业务
    -17.00
    rieve
    -17.00
    营业执照
    -17.00
    收购
    -16.88
    评估
    -16.88
    olicit
    -16.75
    _sink
    -16.50
    POSITIVE LOGITS
     gears
    27.75
     gear
    26.13
     Gear
    24.75
    传动
    23.88
    Gear
    23.38
    trans
    23.13
     transmission
    22.13
     trans
    22.13
    -trans
    22.00
    gear
    22.00
    Activations Density 0.079%

    No Known Activations