© 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. 16709
    Prev
    Next
    INDEX
    Explanations

    name prefixes and suffixes

    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
    wol
    -0.06
    ÑĢиз
    -0.05
    bé
    -0.05
    使å¾Ĺ
    -0.05
    wal
    -0.05
    æĹłç©·çļĦ
    -0.05
    ä¸ĬçļĦ
    -0.05
    icular
    -0.05
    ÑĢÑĤе
    -0.05
    PUTE
    -0.05
    POSITIVE LOGITS
    æĪijçĪ±
    0.06
     дваждÑĭ
    0.06
    versch
    0.06
    جز
    0.05
    éģĵåıĭ
    0.05
     Ñī
    0.05
    éĤĢ
    0.05
    宣讲ä¼ļ
    0.05
    ljed
    0.05
    举ä¸Ģåıįä¸ī
    0.05
    Activations Density 0.002%

    No Known Activations