© 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. 2183
    Prev
    Next
    INDEX
    Explanations

    say legion

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

    No Comments

    Negative Logits
     Jer
    -18.00
    ‖
    -17.75
    .verify
    -17.00
    治
    -16.88
     pen
    -16.50
     deriv
    -16.50
     reflective
    -16.38
     analog
    -15.94
    derive
    -15.94
    (register
    -15.81
    POSITIVE LOGITS
     Legion
    30.38
     legion
    29.38
    军团
    25.75
    colon
    22.63
     demon
    22.63
    Demon
    21.13
    共振
    20.25
     Demon
    19.63
     Colon
    18.88
    Colon
    18.75
    Activations Density 0.134%

    No Known Activations