© 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. 986
    Prev
    Next
    INDEX
    Explanations

    city names

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Irish
    -37.25
     Ireland
    -36.50
     Belfast
    -36.00
    湖北省
    -35.50
    爱尔兰
    -35.25
    襄阳
    -35.00
    武汉市
    -33.25
    湖北
    -32.25
     Gael
    -32.00
    武汉
    -31.50
    POSITIVE LOGITS
    芥
    22.63
    榧
    22.00
    雅
    21.50
    亚马逊
    21.25
     Pasadena
    20.50
     Nik
    20.50
     Florence
    19.38
    淄博
    18.75
    oren
    18.63
     Olympia
    18.63
    Activations Density 0.361%

    No Known Activations