© 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. 3097
    Prev
    Next
    INDEX
    Explanations

    pipe separators

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    砰
    -20.75
    精力
    -18.88
    浮动
    -17.00
    izador
    -16.50
    ProcessEvent
    -16.50
    こちら
    -16.25
    {}",
    -16.25
    .appspot
    -16.13
     PROFITS
    -16.13
    weather
    -15.88
    POSITIVE LOGITS
     cop
    14.44
    ed
    14.25
    #
    13.81
     prost
    13.75
     nhu
    13.63
    edes
    13.56
    麓
    13.56
    arrow
    13.50
    |
    13.25
     tire
    13.25
    Activations Density 0.028%

    No Known Activations