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

    Neuronpedia

    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. 41
    Prev
    Next
    INDEX
    Explanations

    say places

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

    No Comments

    Negative Logits
    伯
    -19.00
     Halifax
    -19.00
    鹅
    -18.13
     Hampshire
    -16.88
    _FT
    -16.63
     VT
    -15.75
    新加坡
    -15.63
     Murdoch
    -15.56
     Beirut
    -15.50
    华人
    -15.44
    POSITIVE LOGITS
    安徽省
    37.75
     Polish
    33.75
    合肥市
    33.50
    蚌埠
    33.25
     UW
    32.25
    合肥
    32.00
     Warsaw
    31.38
    波兰
    30.63
    皖
    30.38
    安徽
    29.63
    Activations Density 0.042%

    No Known Activations