© 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. 14094
    Prev
    Next
    INDEX
    Explanations

    say capture

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

    No Comments

    Negative Logits
     projects
    -21.25
     project
    -20.25
    _projects
    -19.88
    实验
    -19.88
    项目
    -19.13
    _project
    -19.00
    projects
    -18.88
     Extension
    -18.50
    _poly
    -18.38
    Projects
    -18.13
    POSITIVE LOGITS
     capture
    24.50
     capturing
    22.13
     Capture
    21.88
    capture
    21.50
     captures
    21.38
    Capture
    20.13
    captures
    20.00
     captured
    19.75
    .capture
    18.88
    Capt
    18.25
    Activations Density 0.635%

    No Known Activations