© 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. 15778
    Prev
    Next
    INDEX
    Explanations

    say "ac"

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

    No Comments

    Negative Logits
    -sh
    -41.50
    Sh
    -41.50
    /sh
    -40.75
     Sh
    -40.25
    	sh
    -39.75
    sh
    -39.00
    (sh
    -38.50
     sh
    -37.75
     Shark
    -37.25
     shale
    -37.25
    POSITIVE LOGITS
    /ac
    18.25
     Spencer
    17.25
     spo
    17.25
    飏
    16.88
     xo
    16.88
    _tw
    16.75
     tuner
    16.63
    acet
    16.63
     sac
    16.25
    -ac
    16.13
    Activations Density 6.128%

    No Known Activations