© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14508
    Prev
    Next
    INDEX
    Explanations

    say "ton"

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

    No Comments

    Negative Logits
    赌博
    -18.00
    赞助
    -17.88
    spo
    -17.25
    镶
    -16.63
    庄园
    -15.94
    ListComponent
    -15.81
    .REG
    -15.69
    endcode
    -15.63
    .addProperty
    -15.56
     BANK
    -15.50
    POSITIVE LOGITS
     tones
    20.50
     tons
    20.13
     ton
    19.75
    -ton
    19.00
     Ton
    18.88
    Ton
    17.75
     Tone
    17.75
    otive
    16.88
    TON
    16.50
     tone
    16.38
    Activations Density 0.041%

    No Known Activations