© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15564
    Prev
    Next
    INDEX
    Explanations

    heraldic terms

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

    No Comments

    Negative Logits
     Bamboo
    -19.13
    襟
    -18.25
     bamboo
    -18.00
    民营经济
    -17.88
    风光
    -17.75
    文化节
    -17.63
    apan
    -17.00
    ObjectContext
    -16.75
     wind
    -16.50
    enna
    -16.50
    POSITIVE LOGITS
     descriptors
    14.06
    杀
    13.88
     killers
    13.81
     antis
    13.75
     Hom
    13.75
    不克
    13.63
     sympt
    13.63
     Cassidy
    13.56
    :params
    13.38
     hom
    13.31
    Activations Density 0.025%

    No Known Activations