© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15725
    Prev
    Next
    INDEX
    Explanations

    say cables

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

    No Comments

    Negative Logits
    lake
    -18.88
    海棠
    -17.38
    buckets
    -17.38
    bucket
    -16.75
    池
    -16.63
     Pool
    -16.50
    焦点
    -16.13
    (pool
    -15.81
     pool
    -15.63
     PointF
    -15.38
    POSITIVE LOGITS
     cables
    30.38
    电缆
    30.25
     cable
    28.63
    缆
    28.13
     Cable
    26.88
    电线
    24.25
    铜
    24.13
     wires
    23.88
     wire
    23.50
     copper
    23.38
    Activations Density 0.200%

    No Known Activations