© 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
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15562
    Prev
    Next
    INDEX
    Explanations

    names

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

    No Comments

    Negative Logits
    .kr
    -20.38
    IRC
    -20.13
    .mx
    -19.50
    IRR
    -18.88
    OLS
    -18.88
    LL
    -18.88
    .lr
    -18.63
    ILI
    -18.50
     XR
    -18.50
    VRT
    -18.50
    POSITIVE LOGITS
    通行证
    16.25
     threading
    16.00
    灯火
    15.44
    舞蹈
    15.13
    thread
    15.06
     dances
    15.00
     Hancock
    14.94
    舞
    14.75
     dancers
    14.50
     thread
    14.44
    Activations Density 0.428%

    No Known Activations