© 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. 15705
    Prev
    Next
    INDEX
    Explanations

    say address

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

    No Comments

    Negative Logits
    編
    -19.13
     den
    -16.88
    ogui
    -15.94
    /compiler
    -15.81
    -den
    -15.69
    加密
    -15.63
    /widgets
    -15.44
     edit
    -15.31
     Den
    -15.13
    Den
    -15.00
    POSITIVE LOGITS
    -address
    18.50
    addr
    18.13
     Address
    17.38
    鸫
    17.38
    Address
    17.38
     address
    17.25
    .addr
    17.25
    raised
    17.25
    ADDRESS
    17.25
     adr
    17.13
    Activations Density 0.397%

    No Known Activations