© 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. 22539
    Prev
    Next
    INDEX
    Explanations

    keep an eye on

    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
    ousy
    -0.07
    ãĤ¿ãĤ¯
    -0.06
     airstrikes
    -0.06
    ajara
    -0.06
     СимпÑĤо
    -0.06
    yo
    -0.06
    åĵªä¸Ģ个
    -0.06
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    -0.06
    åĶ¯ä¸Ģä¸Ģ个
    -0.06
    ingo
    -0.06
    POSITIVE LOGITS
     Ñģебе
    0.06
     it
    0.05
     íķ¨
    0.05
    Ø¢ÙĨ
    0.05
    åĴĮ
    0.05
     and
    0.05
    æľ¬æĬ¥åijĬ
    0.05
    èĩªå·±çļĦçĶŁåij½
    0.05
    prib
    0.05
    ÏĢοίη
    0.05
    Activations Density 0.021%

    No Known Activations