© 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. 753
    Prev
    Next
    INDEX
    Explanations

    say building floors

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

    No Comments

    Negative Logits
     trout
    -21.13
    deer
    -20.75
    农家
    -19.88
    骑行
    -19.13
    Oregon
    -19.00
    鳅
    -18.50
     cider
    -18.25
     vinegar
    -18.13
    捕鱼
    -18.13
     Hunting
    -18.00
    POSITIVE LOGITS
     skys
    27.75
    楼
    23.50
     floors
    23.38
    大楼
    23.38
    大厦
    23.25
     floor
    22.88
    楼层
    22.38
     Floor
    22.25
    写字楼
    22.25
     tower
    21.63
    Activations Density 0.089%

    No Known Activations