© 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. 2342
    Prev
    Next
    INDEX
    Explanations

    say "em" words

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

    No Comments

    Negative Logits
     ctx
    -19.13
    (ctx
    -18.38
    .registry
    -17.25
     δ
    -17.13
    ctx
    -17.13
    丙
    -16.00
    	ctx
    -15.69
    厂区
    -15.25
    夏
    -15.25
     millennium
    -15.19
    POSITIVE LOGITS
     Em
    60.25
    Em
    59.50
     emotion
    56.75
    情感
    56.75
     em
    56.00
    (em
    55.00
     emotional
    53.25
    	em
    53.00
    -em
    52.75
    的情感
    52.25
    Activations Density 0.273%

    No Known Activations