© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 545
    Prev
    Next
    INDEX
    Explanations

    say "M" words

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

    No Comments

    Negative Logits
    邢台
    -13.94
    xEB
    -13.81
    承德
    -13.63
    adesh
    -13.50
    itore
    -13.13
    커
    -13.00
    ernes
    -12.94
    河北省
    -12.88
    OfBirth
    -12.75
     IDb
    -12.69
    POSITIVE LOGITS
     MT
    53.25
     MB
    52.25
     MF
    50.25
     MX
    49.50
    MT
    49.25
     MC
    49.00
    (mb
    48.25
     MD
    48.00
    MB
    47.25
    MF
    47.25
    Activations Density 2.208%

    No Known Activations