© 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. 22381
    Prev
    Next
    INDEX
    Explanations

    code symbols and comments

    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
    ë³µ
    -0.06
    ith
    -0.05
    ito
    -0.05
    loss
    -0.05
    rase
    -0.05
    arry
    -0.05
     ë³µ
    -0.05
    èĤ¡
    -0.05
    ä¸įæĪIJ
    -0.05
     Consequently
    -0.05
    POSITIVE LOGITS
    inage
    0.06
    онаÑĤ
    0.06
    avier
    0.06
     ÙħÙĨÙĩÙħا
    0.06
    人çļĦçĶŁåij½
    0.06
    olid
    0.06
    props
    0.06
     TUY
    0.06
    æľĿåįĹ
    0.05
    æĹ¥æĬ¥ç¤¾
    0.05
    Activations Density 0.060%

    No Known Activations