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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14241
    Prev
    Next
    INDEX
    Explanations

    say website words

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

    No Comments

    Negative Logits
     labour
    -18.50
     recognise
    -17.25
     recognised
    -17.25
    Exports
    -16.38
    熨
    -16.00
    	Render
    -15.63
     organis
    -15.50
     jewellery
    -15.31
     sediment
    -15.25
     organise
    -15.19
    POSITIVE LOGITS
    网站
    26.75
    账号
    21.63
    用户
    21.25
    站长
    20.75
    网址
    20.75
    网络
    20.63
    网站建设
    20.25
    网友
    20.13
    登录
    19.75
    门户
    19.63
    Activations Density 0.460%

    No Known Activations