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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15941
    Prev
    Next
    INDEX
    Explanations

    say "汤" words

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

    No Comments

    Negative Logits
     Musk
    -18.00
    レベル
    -17.63
    四级
    -17.25
    ussia
    -16.13
     Ranch
    -15.94
    growth
    -15.88
    級
    -15.44
     Sens
    -15.38
     Sensor
    -15.19
     Beds
    -15.19
    POSITIVE LOGITS
    汤
    16.25
    冲
    15.94
    煮
    15.50
    温
    15.25
    ither
    15.06
    服
    14.69
    �
    14.56
    一时
    14.44
    溶
    14.25
    斟
    14.25
    Activations Density 0.130%

    No Known Activations