© 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. 2280
    Prev
    Next
    INDEX
    Explanations

    say "terminology"

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

    No Comments

    Negative Logits
    uges
    -17.25
    [res
    -16.25
    ordes
    -15.81
    保
    -15.69
    爸爸
    -15.56
    .TR
    -15.19
    丙
    -15.13
    =req
    -15.00
    (req
    -14.75
    edian
    -14.69
    POSITIVE LOGITS
    Ter
    63.25
     Termin
    58.75
     termin
    57.75
    termin
    56.75
     Ter
    54.75
     ter
    54.00
     TERMIN
    51.50
     terminology
    49.50
    TER
    49.00
    ter
    47.75
    Activations Density 0.046%

    No Known Activations