© 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. 16614
    Prev
    Next
    INDEX
    Explanations

    rolling powder, dough, or carpet

    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
    èģļåIJĪ
    -0.05
    ç§į
    -0.05
     le
    -0.05
     кеÑĢ
    -0.05
    é¦ĸéĥ¨
    -0.05
    ago
    -0.05
    _closed
    -0.05
    ades
    -0.05
    anza
    -0.05
    response
    -0.05
    POSITIVE LOGITS
    occo
    0.06
    åĪĨ享èĩ³
    0.06
    ouv
    0.06
    åĽĽæ°Ł
    0.06
     طا
    0.06
    ocrisy
    0.06
    å¹³æķ´
    0.06
    æĸ°å±Ģ
    0.06
     raya
    0.06
    iaz
    0.06
    Activations Density 0.003%

    No Known Activations