© 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. 15924
    Prev
    Next
    INDEX
    Explanations

    say water

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

    No Comments

    Negative Logits
    mant
    -18.38
    Embed
    -17.88
    porte
    -16.88
    百科
    -16.38
    VEST
    -16.25
    rossover
    -16.13
     embeddings
    -16.00
     embedding
    -15.88
    火星
    -15.75
     Embed
    -15.69
    POSITIVE LOGITS
     water
    30.88
    供水
    30.25
    水源
    29.13
    饮用水
    28.25
     Water
    28.13
    Water
    28.00
    自来水
    27.88
    水资源
    27.50
    净水
    27.38
    水
    27.13
    Activations Density 0.312%

    No Known Activations