© 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. 2476
    Prev
    Next
    INDEX
    Explanations

    att

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

    No Comments

    Negative Logits
     MER
    -17.88
    props
    -16.88
     props
    -16.88
    MER
    -16.63
     recursion
    -16.25
    proposal
    -15.94
    ��
    -15.81
    olon
    -15.63
    dict
    -15.50
    回购
    -15.25
    POSITIVE LOGITS
     Att
    52.25
    (att
    51.75
     att
    49.25
    Att
    48.00
    att
    43.75
    _att
    43.25
    .att
    41.00
    _ATT
    35.50
     attenu
    34.75
     attenuation
    33.75
    Activations Density 0.118%

    No Known Activations