© 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. 2577
    Prev
    Next
    INDEX
    Explanations

    say "ref"

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

    No Comments

    Negative Logits
    記
    -23.50
    记
    -23.25
     pollen
    -20.38
    Poll
    -19.25
    poll
    -19.00
     Poll
    -18.25
     poll
    -17.63
    .poll
    -17.38
    _poll
    -17.00
    投票
    -17.00
    POSITIVE LOGITS
    (ref
    44.25
    Ref
    42.00
     refugees
    41.25
     Refuge
    39.25
     ref
    39.00
     Ref
    38.75
     refugee
    38.00
    	ref
    38.00
    _ref
    37.25
    ref
    37.00
    Activations Density 0.075%

    No Known Activations