© 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. 16602
    Prev
    Next
    INDEX
    Explanations

    gastric emptying and glucose metabolism

    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
    zuk
    -0.06
    å¤ļåģļ
    -0.06
    pez
    -0.06
    okon
    -0.06
    åij½ä»¤
    -0.06
     تÙĥ
    -0.06
     thừa
    -0.06
    ÑģÑĤо
    -0.06
    gev
    -0.05
    _drive
    -0.05
    POSITIVE LOGITS
    è¡Ģç³ĸ
    0.05
    emo
    0.05
    èĩªå·±çļĦæĥħ绪
    0.05
    agog
    0.05
    ä¸ĢæĻĥ
    0.05
    ิà¸ĩ
    0.05
    ADER
    0.05
    èIJ½å·®
    0.05
    ÙħÙĩ
    0.05
    å»¶è¿Ł
    0.05
    Activations Density 0.024%

    No Known Activations