© 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. 16381
    Prev
    Next
    INDEX
    Explanations

    say "deep"

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

    No Comments

    Negative Logits
    .zone
    -20.00
    惮
    -19.00
    _zone
    -18.13
    DOMNode
    -17.63
    CORD
    -17.63
     bead
    -17.50
    -zone
    -17.50
     breeze
    -17.38
    .ico
    -17.38
    oard
    -17.38
    POSITIVE LOGITS
    深
    17.88
    科学家
    15.75
    自然科学
    15.19
     Picasso
    13.94
     Luther
    13.63
    嵌
    13.13
     deepest
    13.13
     deeper
    13.00
    鲁迅
    13.00
     Bur
    12.81
    Activations Density 1.199%

    No Known Activations