© 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. 16752
    Prev
    Next
    INDEX
    Explanations

    `"` or `]` after keywords

    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
    æĬ¬å¤´
    -0.07
    rÃŃa
    -0.06
    åĩĮ
    -0.06
    è¯ĿæĿ¥
    -0.06
    çijŀ
    -0.05
    ummy
    -0.05
    å¤ĦçIJĨæĸ¹å¼ı
    -0.05
     Barca
    -0.05
     superf
    -0.05
    åŀ
    -0.05
    POSITIVE LOGITS
    дÑĢо
    0.06
    ав
    0.05
    สิà¹īà¸Ļ
    0.05
     preko
    0.05
    ieber
    0.05
    aut
    0.05
    åĽ¾ä¸Ń
    0.05
    (Filter
    0.05
    ade
    0.05
    erek
    0.05
    Activations Density 0.002%

    No Known Activations