© 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. 16556
    Prev
    Next
    INDEX
    Explanations

    method and apparatus

    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
    对该
    -0.06
    ova
    -0.06
    =o
    -0.06
    ç±»åŀĭçļĦ
    -0.06
    åı£çļĦ
    -0.05
    åIJĦé¡¹çĽ®
    -0.05
    ov
    -0.05
    对她
    -0.05
    lh
    -0.05
    ovas
    -0.05
    POSITIVE LOGITS
     patented
    0.07
    olling
    0.06
    ÑĪеÑĤ
    0.06
    à¸Īà¸ĩ
    0.06
    å¼ķè¿ĽäºĨ
    0.06
    ubb
    0.06
    æĽ¸è¨ĺ
    0.05
    ниÑģ
    0.05
    oire
    0.05
     mej
    0.05
    Activations Density 1.149%

    No Known Activations