© 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. 22299
    Prev
    Next
    INDEX
    Explanations

    code keywords

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¹³
    -0.06
    aw
    -0.05
    acer
    -0.05
    æİĴ
    -0.05
    -0.05
     Union
    -0.05
    ech
    -0.05
    éĻ¢
    -0.05
    ingers
    -0.05
    Union
    -0.05
    POSITIVE LOGITS
    chiere
    0.07
    ä¸Ńå¿ĥåĴĮ
    0.07
     cerem
    0.06
    ä¸įå°ijçļĦ
    0.06
     Diri
    0.06
    çĶ±é«ĺ
    0.06
     ÙħÙĨا
    0.06
     isted
    0.06
     disipl
    0.06
     nutris
    0.06
    Activations Density 0.020%

    No Known Activations