© 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. 15544
    Prev
    Next
    INDEX
    Explanations

    say "clear"

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

    No Comments

    Negative Logits
    athi
    -15.81
    mö
    -15.50
    ervo
    -15.44
    押金
    -15.25
    汉堡
    -15.13
     Ry
    -15.06
     sewing
    -14.81
     Emoji
    -14.56
     ants
    -14.56
     emoji
    -14.56
    POSITIVE LOGITS
    清
    44.25
    -clear
    44.00
     clear
    42.75
     Clear
    42.25
     clears
    41.50
     cleared
    41.25
     clarity
    41.25
    Clear
    40.50
    clear
    40.50
    清晰
    39.50
    Activations Density 0.312%

    No Known Activations