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

    Neuronpedia

    Jacobian LensNEW
    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. 1339
    Prev
    Next
    INDEX
    Explanations

    say programming identifiers

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

    No Comments

    Negative Logits
    葡萄牙
    -20.25
    _paper
    -19.25
     papel
    -19.13
    编程
    -18.63
    metal
    -18.00
    纸
    -17.88
    elenium
    -17.75
     paper
    -17.75
    мет
    -17.38
    金华
    -17.13
    POSITIVE LOGITS
     byte
    22.50
    byte
    21.25
    盐
    20.38
    -byte
    20.00
     salt
    19.88
     Salt
    19.25
     字
    19.25
     token
    19.00
    tokenId
    19.00
    -Token
    18.63
    Activations Density 0.235%

    No Known Activations