© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14518
    Prev
    Next
    INDEX
    Explanations

    class attribute

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

    No Comments

    Negative Logits
    AMPL
    -18.25
    油田
    -18.00
    aqu
    -17.50
     Lamar
    -17.13
    NEY
    -17.00
     Mey
    -17.00
    ebb
    -16.88
    堰
    -16.50
     oils
    -16.38
    Writable
    -16.38
    POSITIVE LOGITS
    -sh
    17.50
    clone
    17.25
    Subtitle
    16.00
    arta
    15.94
    Sprite
    15.81
    -runtime
    15.44
    rt
    15.31
    旭
    15.25
    ute
    14.88
    ssf
    14.88
    Activations Density 0.062%

    No Known Activations