© 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. 15436
    Prev
    Next
    INDEX
    Explanations

    say arch

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

    No Comments

    Negative Logits
    Peak
    -18.25
    peak
    -18.00
    山村
    -16.63
    pery
    -16.50
    .Pending
    -16.38
    (Stream
    -16.38
    setSize
    -16.38
    鬓
    -16.25
    iali
    -16.25
     Peak
    -16.25
    POSITIVE LOGITS
     arch
    19.00
     Arch
    18.88
    Arch
    18.00
     archae
    17.63
     Archae
    17.13
     Archives
    16.63
    .arch
    16.63
    arch
    16.38
    prot
    16.00
     Pro
    15.75
    Activations Density 0.092%

    No Known Activations