© 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. 15341
    Prev
    Next
    INDEX
    Explanations

    say table

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

    No Comments

    Negative Logits
    背景
    -19.38
     background
    -19.25
    Background
    -18.13
    BACKGROUND
    -18.13
     Background
    -17.75
     ZEND
    -17.50
    bane
    -17.25
    -background
    -16.88
    _BACKGROUND
    -16.63
    血液
    -16.13
    POSITIVE LOGITS
    gran
    16.25
    .dds
    14.63
     entries
    14.38
     Entries
    14.19
    physical
    13.94
     gar
    13.88
    <thead
    13.88
    entry
    13.81
    <Entry
    13.75
     carved
    13.69
    Activations Density 0.015%

    No Known Activations