© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1392
    Prev
    Next
    INDEX
    Explanations

    Roman

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

    No Comments

    Negative Logits
     Roman
    -54.50
    罗马
    -53.00
     Rome
    -48.50
     Romans
    -48.25
    Roman
    -47.25
     roman
    -44.50
    roman
    -42.50
     Roma
    -39.25
     ROM
    -38.25
    Rom
    -37.25
    POSITIVE LOGITS
     ENERGY
    18.00
     energy
    17.50
    Energy
    17.38
     Energy
    16.88
     DK
    15.88
    energy
    14.81
    ijkl
    14.50
    DK
    14.19
    Keyword
    14.19
    _energy
    14.06
    Activations Density 0.106%

    No Known Activations