© 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. 2786
    Prev
    Next
    INDEX
    Explanations

    resolution

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

    No Comments

    Negative Logits
     ANT
    -16.75
     antis
    -15.81
     Ant
    -15.81
    .ant
    -15.75
    emet
    -15.69
    押
    -15.25
    蚁
    -15.19
    Ant
    -15.00
     Katy
    -14.88
    老头
    -14.88
    POSITIVE LOGITS
     resolution
    66.50
     Resolution
    64.50
     resolutions
    63.00
    Resolution
    63.00
    resolution
    59.75
     resolved
    56.50
     resolver
    54.75
    .resolution
    54.75
    _resolution
    54.50
     resolve
    53.00
    Activations Density 0.156%

    No Known Activations