© 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. 16264
    Prev
    Next
    INDEX
    Explanations

    say "transfer"

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

    No Comments

    Negative Logits
    =temp
    -17.00
    ologue
    -16.63
     YM
    -16.38
    -template
    -16.13
    hook
    -16.13
    ropol
    -16.00
    .soft
    -15.81
    钩
    -15.63
    -hook
    -15.63
    CLE
    -15.56
    POSITIVE LOGITS
     transfer
    24.63
    传导
    23.38
     transfers
    22.50
     transferring
    21.88
    -transfer
    21.50
     Transfer
    20.88
     conducts
    20.63
    transfer
    20.25
    con
    20.13
     conduct
    20.13
    Activations Density 0.137%

    No Known Activations