© 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. 16695
    Prev
    Next
    INDEX
    Explanations

    intelligent design, principle, Total, classic, contradiction, axonal

    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
    æ½ľ
    -0.06
    认åIJĮ
    -0.06
    ÙĦب
    -0.06
    verd
    -0.06
    åľº
    -0.06
    佩
    -0.06
    çݯå¢ĥçĽijæµĭ
    -0.06
    antau
    -0.05
    éķ·éģĶ
    -0.05
    客ä½ĵ
    -0.05
    POSITIVE LOGITS
    èµ°ä¸Ĭ
    0.06
    æľī个
    0.05
    onta
    0.05
    åĴĮå¹³
    0.05
    ç§ģç«ĭ
    0.05
     gratuit
    0.05
     jar
    0.05
    éĻ¡
    0.05
     examples
    0.05
    æ¯ı次
    0.05
    Activations Density 0.019%

    No Known Activations