© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1614
    Prev
    Next
    INDEX
    Explanations

    say sound

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

    No Comments

    Negative Logits
     gal
    -52.75
     Gal
    -51.25
    Gal
    -47.25
    gal
    -46.75
     GAL
    -43.50
     galaxies
    -37.75
     galaxy
    -37.25
     widget
    -35.00
     Galactic
    -33.75
    widget
    -32.50
    POSITIVE LOGITS
     sound
    16.00
    美军
    15.19
    JB
    15.13
    索尼
    15.00
    Sony
    14.50
    Sound
    14.38
    笋
    14.25
     Sound
    14.25
    .SO
    14.06
    声音
    14.00
    Activations Density 0.094%

    No Known Activations