© 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. 16590
    Prev
    Next
    INDEX
    Explanations

    appellant, enable, question

    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
    çīĪæĿĥçŃī
    -0.07
    ornos
    -0.07
    lage
    -0.07
    latt
    -0.07
    êµīìŀ¥
    -0.06
    ÑĩиÑĤел
    -0.06
    afür
    -0.06
     calab
    -0.06
    ieger
    -0.06
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.06
    POSITIVE LOGITS
    0.06
     t
    0.05
    chants
    0.05
    表示
    0.05
    形象
    0.05
    漫
    0.05
     S
    0.05
     pas
    0.05
    ared
    0.05
    antic
    0.05
    Activations Density 0.001%

    No Known Activations