© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1440
    Prev
    Next
    INDEX
    Explanations

    say "symbol"

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

    No Comments

    Negative Logits
     fire
    -61.25
    Fire
    -56.25
     Fire
    -55.50
    火
    -54.25
     fires
    -53.50
    -fire
    -53.25
    fire
    -52.75
    	fire
    -52.25
     FIRE
    -51.25
    _fire
    -51.00
    POSITIVE LOGITS
    .ico
    14.75
     symbol
    14.19
    汉
    14.13
    符号
    13.75
     menu
    13.69
    英雄
    13.63
    菜单
    13.25
    勺
    13.13
    .png
    13.00
     Symbol
    13.00
    Activations Density 0.195%

    No Known Activations