© 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. 3355
    Prev
    Next
    INDEX
    Explanations

    say verbs

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    路径
    -19.38
    (configuration
    -18.75
    _configuration
    -17.75
    层
    -17.25
    formation
    -17.00
     formulation
    -16.75
    场上
    -16.25
     Layer
    -16.13
    /configuration
    -16.00
    版本
    -15.94
    POSITIVE LOGITS
     handle
    22.88
     measure
    22.75
    handle
    21.13
     report
    20.25
     address
    19.75
    estimate
    19.75
     estimate
    19.25
     map
    19.25
     share
    18.25
     move
    18.13
    Activations Density 0.282%

    No Known Activations