© 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. 16730
    Prev
    Next
    INDEX
    Explanations

    Russian/Slavic patronymics

    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
    åĮĹç«Ļ
    -0.06
    ICES
    -0.06
    å±ĬæŶ
    -0.05
    apolis
    -0.05
     زاÙĦت
    -0.05
    onsense
    -0.05
    æĸ¹èĥ½
    -0.05
    action
    -0.05
     понÑıÑĤие
    -0.05
     uncomment
    -0.05
    POSITIVE LOGITS
    Ñĸм
    0.06
    edly
    0.06
    ward
    0.06
    cin
    0.06
    indel
    0.06
    à¹Ģà¸ķà¸Ńรà¹Į
    0.06
    å·²ç»ıè¿ĩåİ»
    0.05
    íŀĪ
    0.05
    æĺ¾çĿĢ
    0.05
    æłĩåĩĨè¦ģæ±Ĥ
    0.05
    Activations Density 0.238%

    No Known Activations