© 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. 3184
    Prev
    Next
    INDEX
    Explanations

    say decision

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    cade
    -16.88
    站点
    -16.63
    长度
    -16.50
    	Method
    -16.25
    (site
    -15.63
    ois
    -15.38
     getPath
    -15.19
    apeut
    -15.13
    .site
    -15.13
     site
    -14.94
    POSITIVE LOGITS
     decision
    41.25
    decision
    39.50
    决策
    34.00
     Decision
    34.00
    Decision
    32.25
    _decision
    30.00
     decisions
    25.00
     decisión
    20.50
     department
    20.13
     décision
    20.13
    Activations Density 0.167%

    No Known Activations