© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 818
    Prev
    Next
    INDEX
    Explanations

    say place names

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NEC
    -18.25
    	es
    -18.00
     PEM
    -17.88
     VX
    -17.50
    ESP
    -17.50
     Gomez
    -17.25
     CCT
    -16.75
     ES
    -16.75
     IPS
    -16.63
    荞
    -16.63
    POSITIVE LOGITS
    昆仑
    27.63
     Fiona
    23.38
     Athens
    22.00
    _IA
    21.75
    欧
    21.63
    奥林匹
    21.63
     Москов
    20.75
    郴州
    20.25
    希腊
    20.25
     Boise
    20.25
    Activations Density 0.276%

    No Known Activations