© 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. 2452
    Prev
    Next
    INDEX
    Explanations

    heritage

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

    No Comments

    Negative Logits
    Sim
    -18.00
     simulation
    -17.50
    (sim
    -17.25
     sims
    -16.75
     simul
    -16.63
    simulation
    -16.50
     Sim
    -16.25
    lik
    -16.13
    simulate
    -16.00
     sim
    -15.88
    POSITIVE LOGITS
    遗产
    37.75
     heritage
    34.00
    herit
    32.50
     Heritage
    30.50
     legacy
    30.25
     Legacy
    28.63
    Legacy
    27.88
     inherit
    27.50
    遺
    26.88
    祖
    25.50
    Activations Density 0.084%

    No Known Activations