© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 782
    Prev
    Next
    INDEX
    Explanations

    say rs

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

    No Comments

    Negative Logits
     Cavs
    -21.50
     Akron
    -16.88
     Pyongyang
    -16.75
     ECB
    -16.75
     Ky
    -16.38
    爱尔兰
    -16.13
     Donetsk
    -16.13
    鲅
    -16.00
     tob
    -15.69
     Ukrainian
    -15.56
    POSITIVE LOGITS
     RS
    68.00
     rs
    64.50
    (rs
    62.75
    RS
    60.75
    /rs
    57.75
    rs
    56.25
    	rs
    56.25
    _rs
    56.00
    _RS
    50.75
    $rs
    45.00
    Activations Density 0.039%

    No Known Activations