© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16304
    Prev
    Next
    INDEX
    Explanations

    say adhesive

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

    No Comments

    Negative Logits
    羌
    -17.88
     rotated
    -17.25
    部部长
    -16.88
    uran
    -16.75
     Canberra
    -16.63
     Shah
    -16.63
    延安
    -16.38
    骷
    -16.25
     Royals
    -15.69
     Uran
    -15.69
    POSITIVE LOGITS
    粘
    30.75
     adhesive
    29.88
     bonds
    28.25
     bond
    28.00
    黏
    27.50
     glue
    27.25
    胶
    27.13
     bonding
    26.50
     Bonds
    26.00
     Sticky
    25.63
    Activations Density 0.224%

    No Known Activations