© 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. 15790
    Prev
    Next
    INDEX
    Explanations

    say "log"

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

    No Comments

    Negative Logits
    篱
    -17.13
    马桶
    -16.75
     chimney
    -16.63
    墙面
    -16.63
     objective
    -16.25
    bull
    -16.13
    萤
    -16.00
     Calder
    -15.69
     Roulette
    -15.63
     станд
    -15.25
    POSITIVE LOGITS
     Log
    18.50
    _Log
    18.00
    Log
    17.88
     logs
    17.75
    LOG
    17.75
     log
    17.63
    log
    17.50
    -log
    16.75
     Trinity
    16.25
     LOG
    16.13
    Activations Density 0.086%

    No Known Activations