© 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. 2884
    Prev
    Next
    INDEX
    Explanations

    Holy Spirit

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

    No Comments

    Negative Logits
    quo
    -20.00
    Race
    -18.50
    _UTIL
    -18.50
     ethnicity
    -17.75
     Ethnic
    -17.50
    脱发
    -17.25
    CCA
    -17.13
    绒
    -17.00
     hairstyle
    -17.00
     Labour
    -17.00
    POSITIVE LOGITS
     breathed
    15.56
    rx
    15.50
    ampus
    15.19
    烟
    14.63
     tor
    14.44
    燃烧
    14.38
     breathe
    14.25
    喉
    14.00
     sd
    13.81
     Ney
    13.69
    Activations Density 0.156%

    No Known Activations