© 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. 549
    Prev
    Next
    INDEX
    Explanations

    say g endings

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

    No Comments

    Negative Logits
     Fior
    -13.81
    ERRY
    -13.75
    okit
    -13.31
     reg
    -13.06
    lymp
    -13.00
    ruc
    -12.94
    esity
    -12.69
    葵
    -12.63
    ucker
    -12.63
    eric
    -12.56
    POSITIVE LOGITS
     PG
    63.00
     SG
    63.00
     DG
    59.75
     MG
    59.25
     CG
    59.00
    PG
    58.75
     TG
    57.00
     cg
    56.75
    SG
    56.50
     LG
    55.75
    Activations Density 0.627%

    No Known Activations