© 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. 2248
    Prev
    Next
    INDEX
    Explanations

    say "ep"

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

    No Comments

    Negative Logits
    Reserved
    -16.75
    保留
    -16.50
     reserve
    -16.38
     conserv
    -16.13
     conserve
    -16.13
     conservative
    -15.38
     Reserved
    -15.38
     retained
    -15.25
     resign
    -15.13
    facet
    -14.94
    POSITIVE LOGITS
     Ep
    18.50
    (memory
    17.88
     epilepsy
    17.25
    癫痫病
    17.25
     Magick
    16.88
     ép
    16.75
    Ep
    16.75
     memory
    16.63
     epile
    16.50
    (ep
    16.25
    Activations Density 0.018%

    No Known Activations