© 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. 22491
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating movement or relation

    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
    paren
    -0.06
     separate
    -0.05
    æľĢåIJİçļĦ
    -0.05
     наконеÑĨ
    -0.05
     discretion
    -0.05
    æľĢåIJİ
    -0.05
    æľ«
    -0.05
     Separate
    -0.05
    antisipasi
    -0.05
    çĭ¬ç«ĭçļĦ
    -0.05
    POSITIVE LOGITS
    afa
    0.06
    ä¹Ŀå·ŀ
    0.06
    æīģæ¡ĥ
    0.06
     prossime
    0.06
    ä¾µ
    0.06
    جØŃ
    0.06
    itti
    0.05
    -feedback
    0.05
    GOR
    0.05
    पà¥įत
    0.05
    Activations Density 0.008%

    No Known Activations