© 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. 16273
    Prev
    Next
    INDEX
    Explanations

    say name

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

    No Comments

    Negative Logits
     canvas
    -15.81
     Ethernet
    -15.69
    四肢
    -15.25
    门槛
    -14.75
     HDR
    -14.56
    canvas
    -14.56
    手脚
    -14.44
    sek
    -14.06
    Ethernet
    -14.00
    モデル
    -14.00
    POSITIVE LOGITS
    名字
    49.25
     name
    48.50
     names
    47.25
    的名字
    46.75
    命名
    45.25
    名称
    43.50
     Name
    43.25
    name
    43.25
     naming
    43.00
    名
    42.25
    Activations Density 0.521%

    No Known Activations