© 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. 15481
    Prev
    Next
    INDEX
    Explanations

    say press

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

    No Comments

    Negative Logits
    剪
    -25.50
     sh
    -25.00
    	sh
    -24.88
    滑雪
    -24.75
     Shuffle
    -24.63
    鞋
    -24.00
    -sh
    -23.88
     shading
    -23.63
     skew
    -23.38
    Sh
    -23.13
    POSITIVE LOGITS
    变压
    19.50
    _press
    19.00
    postgres
    18.88
    acr
    18.50
    _pressure
    18.25
    Pu
    18.25
    press
    17.88
    溴
    17.88
     cred
    17.75
    邕
    17.75
    Activations Density 5.677%

    No Known Activations