© 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. 1060
    Prev
    Next
    INDEX
    Explanations

    [Emotional] => [Emotional]

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

    No Comments

    Negative Logits
     emotional
    -52.00
     emotion
    -50.75
     emotions
    -49.50
     Emotional
    -48.00
    情感
    -45.75
     emotionally
    -44.75
    emotion
    -40.00
    的情感
    -37.25
     emoc
    -36.75
     emot
    -34.25
    POSITIVE LOGITS
    Alpha
    17.88
    .Alpha
    17.38
    alpha
    16.00
    银河
    15.56
    α
    14.88
     α
    14.69
     alpha
    14.63
    _alpha
    14.38
     Alpha
    14.13
    (alpha
    14.13
    Activations Density 0.108%

    No Known Activations