© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16553
    Prev
    Next
    INDEX
    Explanations

    geopolitical entities and allies

    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
    Negative Logits
    åįķæľº
    -0.06
    failure
    -0.06
    -link
    -0.06
    æĬ¢
    -0.05
     alcald
    -0.05
     failure
    -0.05
    çĽij
    -0.05
    åĪ«
    -0.05
    iere
    -0.05
    anak
    -0.05
    POSITIVE LOGITS
    phinx
    0.06
    awan
    0.05
    éģ£
    0.05
     Dien
    0.05
     CrossRef
    0.05
     against
    0.05
    çĸı
    0.05
    èĢĮéĿŀ
    0.05
    æľīèī²
    0.05
    keh
    0.05
    Activations Density 0.088%

    No Known Activations