© 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. 22597
    Prev
    Next
    INDEX
    Explanations

    point of sales, cart, admin, database, application

    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
    ä¸Ģæ°Ķ
    -0.06
     fruition
    -0.06
     ÙħعÙĨا
    -0.06
    æĬķèµĦæľºæŀĦ
    -0.06
    ä¼ģä¸ļæıIJä¾Ľ
    -0.05
    æľīæĦıä¹īçļĦ
    -0.05
    cción
    -0.05
    æł¹æį®æĿĥåĪ©è¦ģæ±Ĥ
    -0.05
    tä
    -0.05
    tive
    -0.05
    POSITIVE LOGITS
    ä¹ł
    0.06
    notice
    0.06
    prefer
    0.05
    nota
    0.05
    æļ¨
    0.05
    leh
    0.05
     incid
    0.05
    éĩijæŃ£
    0.05
    .reserve
    0.05
    yr
    0.05
    Activations Density 0.023%

    No Known Activations