© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15144
    Prev
    Next
    INDEX
    Explanations

    [the] => [the]

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

    No Comments

    Negative Logits
    ple
    -17.88
    lice
    -17.75
    esor
    -17.50
    ication
    -17.00
    uge
    -17.00
    pha
    -16.88
    ledge
    -16.50
    有效的
    -16.50
     freeze
    -16.38
    .freeze
    -16.13
    POSITIVE LOGITS
    <Unit
    14.00
     Alley
    12.94
    Advisor
    12.69
    经开
    12.69
    azen
    12.69
    盖
    12.63
    �
    12.38
    .nb
    12.31
    晚报
    12.25
    千古
    12.19
    Activations Density 0.028%

    No Known Activations