© 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. 15502
    Prev
    Next
    INDEX
    Explanations

    say deep

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

    No Comments

    Negative Logits
    jectives
    -17.50
    Scaler
    -16.75
     Fleming
    -16.25
    /reference
    -15.88
    .refs
    -15.81
    城墙
    -15.81
     Escort
    -15.69
    	ref
    -15.50
    	env
    -15.19
    -reference
    -15.06
    POSITIVE LOGITS
    潜
    19.38
     Detail
    18.38
     detail
    18.25
    奥
    18.25
    深度
    17.38
    detail
    17.25
    layers
    16.88
    深层
    16.63
     Lat
    16.63
     deep
    16.63
    Activations Density 0.301%

    No Known Activations