© 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. 16748
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    åľ°åĿĢä½įäºİ
    -0.06
    ashi
    -0.06
     )"
    -0.06
    æĶ¯æĮģä¸İ
    -0.06
    erton
    -0.06
    orse
    -0.06
     (!((
    -0.06
    ÑģÑĤоиÑĤ
    -0.06
    otis
    -0.06
    alsa
    -0.06
    POSITIVE LOGITS
     từng
    0.06
    à¥ĩà¤Ĥ
    0.06
    ä¸įäºĨ
    0.05
     Åijket
    0.05
     teh
    0.05
    æīĵåį¡
    0.05
     the
    0.05
    atment
    0.05
    大路
    0.05
     each
    0.05
    Activations Density 0.013%

    No Known Activations