© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1362
    Prev
    Next
    INDEX
    Explanations

    emotion words

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

    No Comments

    Negative Logits
    情感
    -32.00
     emotional
    -31.63
     emotions
    -28.13
     emotion
    -28.00
     Emotional
    -27.88
     emotionally
    -26.13
    emotion
    -24.88
    感情
    -23.75
    的情感
    -23.38
     emoc
    -22.38
    POSITIVE LOGITS
    麦
    17.63
    .Alpha
    17.00
     MCU
    16.38
    aju
    16.00
    .Compiler
    15.50
     α
    15.31
     statically
    15.25
    alpha
    15.00
    α
    14.94
     trees
    14.81
    Activations Density 0.059%

    No Known Activations