© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 185
    Prev
    Next
    INDEX
    Explanations

    say "speaking"

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

    No Comments

    Negative Logits
    黑龙
    -21.63
    (HTTP
    -17.25
    东京
    -17.13
    Fluid
    -16.38
    轨道
    -16.25
    厌恶
    -15.88
     Feinstein
    -15.81
    Zen
    -15.81
    HDR
    -15.75
     Appet
    -15.56
    POSITIVE LOGITS
     spoken
    17.63
     speakers
    16.88
     Speakers
    15.38
    讲话
    14.69
    რ
    14.44
    华
    14.25
     speaking
    14.06
     BO
    13.81
    .dialog
    13.81
    華
    13.75
    Activations Density 0.202%

    No Known Activations