© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19880
    Prev
    Next
    INDEX
    Explanations

    SARS and coronavirus diseases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -0.06
    åĵªéĩĮ
    -0.05
    aille
    -0.05
    ist
    -0.05
    身边
    -0.05
    ks
    -0.05
    o
    -0.05
    æĪ¿
    -0.05
    edig
    -0.05
     noc
    -0.05
    POSITIVE LOGITS
    ergi
    0.07
    .GetService
    0.06
    (es
    0.06
    dings
    0.06
     üzere
    0.06
     Energien
    0.06
    otra
    0.06
    令第
    0.06
     اÙĦشعبÙĬ
    0.06
    ulang
    0.06
    Activations Density 0.008%

    No Known Activations