© 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. 1013
    Prev
    Next
    INDEX
    Explanations

    say "mac"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Venezuela
    -24.50
     Venezuel
    -23.25
     Venezuelan
    -21.25
     Riyadh
    -20.25
    济宁
    -19.88
    娄
    -19.88
    石家庄
    -19.75
     Romania
    -19.38
    河北
    -19.00
    安阳
    -18.75
    POSITIVE LOGITS
    (mac
    64.50
     Mac
    63.50
     mac
    61.50
     MAC
    60.25
    mac
    60.25
    Mac
    59.75
    _mac
    57.75
    MAC
    56.75
    .mac
    55.00
    麦
    51.75
    Activations Density 0.203%

    No Known Activations