© 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. 648
    Prev
    Next
    INDEX
    Explanations

    say marsupial words

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

    No Comments

    Negative Logits
     Manitoba
    -19.38
     Scarborough
    -18.88
    Fish
    -17.13
     Ontario
    -16.75
     Saskatchewan
    -16.63
     Fish
    -16.63
     UPC
    -16.50
    пуск
    -16.38
     OC
    -16.38
     province
    -16.25
    POSITIVE LOGITS
     mars
    20.25
     kang
    19.88
     ko
    17.75
     kos
    17.50
    挎
    16.88
     rx
    16.25
     hopping
    16.13
     kissing
    15.94
    kdir
    15.81
    (rx
    15.75
    Activations Density 0.031%

    No Known Activations