© 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. 16652
    Prev
    Next
    INDEX
    Explanations

    United States

    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
    åħ¢
    -0.06
     foul
    -0.06
    ano
    -0.06
    ree
    -0.05
    ceb
    -0.05
     Morm
    -0.05
    ato
    -0.05
    人士
    -0.05
    ount
    -0.05
    uit
    -0.05
    POSITIVE LOGITS
    idler
    0.05
    potensi
    0.05
    алан
    0.05
    kers
    0.05
    zego
    0.05
     majority
    0.05
    entarios
    0.05
    ربت
    0.05
    wegen
    0.05
    èµŀ
    0.05
    Activations Density 0.089%

    No Known Activations