© 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. 2162
    Prev
    Next
    INDEX
    Explanations

    say metaphor

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

    No Comments

    Negative Logits
     perm
    -20.75
    Perm
    -20.13
     Perm
    -19.50
    perm
    -18.50
    perms
    -17.88
    [len
    -17.38
    (ret
    -17.00
     perms
    -16.50
    .Ret
    -16.38
    ret
    -16.25
    POSITIVE LOGITS
    模拟
    46.75
     metaphor
    41.00
     analog
    39.25
    比喻
    37.00
    (sim
    34.25
     Analog
    34.00
     sim
    33.75
     simulate
    32.75
     analogue
    32.50
     simulation
    32.25
    Activations Density 0.087%

    No Known Activations