© 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. 15739
    Prev
    Next
    INDEX
    Explanations

    non‑ASCII characters

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

    No Comments

    Negative Logits
    ADE
    -17.13
    _codegen
    -16.75
     Budapest
    -16.63
    ombok
    -16.50
    vtk
    -16.25
     RTE
    -16.25
    郅
    -15.94
    dde
    -15.63
    .HTML
    -15.44
    -debug
    -15.25
    POSITIVE LOGITS
     Platt
    17.75
    坞
    17.63
     lease
    17.50
    secs
    17.25
    oplay
    17.13
    rimp
    17.00
    conds
    16.88
    coop
    16.63
    clamp
    16.38
    吊
    16.38
    Activations Density 0.842%

    No Known Activations