© 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. 15737
    Prev
    Next
    INDEX
    Explanations

    trend verbs

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

    No Comments

    Negative Logits
    .openg
    -16.88
    ircuit
    -16.00
    caff
    -16.00
    清净
    -15.81
    郏
    -15.50
    efa
    -15.38
    下沉
    -15.31
    .serialization
    -14.88
    涞
    -14.75
     descended
    -14.50
    POSITIVE LOGITS
    mdi
    15.75
     aster
    15.38
    mir
    15.38
    unar
    15.25
    imin
    15.00
    .sign
    14.88
     Statistics
    14.44
    明星
    14.44
     MMI
    14.38
     lsp
    14.25
    Activations Density 0.271%

    No Known Activations