© 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. 15561
    Prev
    Next
    INDEX
    Explanations

    say surface

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

    No Comments

    Negative Logits
    _streams
    -18.00
    隗
    -17.75
    brig
    -17.63
    钟
    -17.50
    ERING
    -17.25
     forks
    -16.63
    .star
    -16.63
     fork
    -16.25
    鐘
    -15.88
     helium
    -15.81
    POSITIVE LOGITS
     surface
    48.00
     surfaces
    44.50
    表面
    44.00
    surface
    43.50
     Surface
    43.00
    Surface
    43.00
    _surface
    39.75
    (surface
    37.50
    .surface
    37.25
    urface
    36.50
    Activations Density 0.333%

    No Known Activations