© 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. 22577
    Prev
    Next
    INDEX
    Explanations

    eeee, ooo, aaaa, yy sounds

    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
    кÑĢ
    -0.05
     miro
    -0.05
    ost
    -0.05
     viên
    -0.05
    çľ¼åīįä¸Ģ亮
    -0.05
    iedo
    -0.05
     convict
    -0.05
    ésar
    -0.05
    kob
    -0.05
    деÑģÑıÑĤ
    -0.05
    POSITIVE LOGITS
    骼
    0.06
    æľĢåIJİä¸Ģ个
    0.06
    _FINAL
    0.06
     Chill
    0.06
    سÛĮ
    0.05
    OfFile
    0.05
     Bett
    0.05
    eren
    0.05
    Gs
    0.05
    gi
    0.05
    Activations Density 0.007%

    No Known Activations