© 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. 16740
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Ùĥذا
    -0.06
     ÙħØŃد
    -0.06
    åĩŃ
    -0.06
     replacement
    -0.06
    è¶ħè¿ĩ约
    -0.05
    gradu
    -0.05
     forc
    -0.05
     maquin
    -0.05
    oard
    -0.05
     esi
    -0.05
    POSITIVE LOGITS
    elve
    0.06
    ä¸ĭ表
    0.06
    iche
    0.06
    åºŀ
    0.06
    bert
    0.06
    rum
    0.06
    ãĤĵãģ³
    0.05
    perk
    0.05
    éĶĻ误æĪĸ
    0.05
    à¹Īà¸Ńà¸ĩ
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.