© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16267
    Prev
    Next
    INDEX
    Explanations

    say "network"

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

    No Comments

    Negative Logits
    膏
    -19.13
    茄
    -18.00
    cursor
    -16.88
    قت
    -15.50
    Samsung
    -15.06
    oused
    -14.88
    鲤
    -14.75
    	cursor
    -14.75
     Israelis
    -14.31
    Honda
    -14.25
    POSITIVE LOGITS
     network
    69.50
    网络
    68.50
     networks
    67.00
    network
    63.25
     Network
    62.00
    Network
    61.50
     Networks
    61.25
    _network
    60.25
     NETWORK
    56.75
    -network
    56.50
    Activations Density 0.313%

    No Known Activations