© 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. 15612
    Prev
    Next
    INDEX
    Explanations

    say "sh"

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

    No Comments

    Negative Logits
    /ac
    -18.25
    _tw
    -18.13
     Spencer
    -17.75
     xo
    -17.50
     spo
    -17.25
     tuner
    -17.25
     lạc
    -17.13
    飏
    -17.13
    acet
    -16.75
    acen
    -16.75
    POSITIVE LOGITS
    Sh
    44.25
    -sh
    43.75
    /sh
    43.25
     Sh
    43.00
    sh
    42.25
    	sh
    41.75
    (sh
    40.75
     sh
    40.25
    _sh
    39.00
    SH
    39.00
    Activations Density 6.211%

    No Known Activations