© 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. 16647
    Prev
    Next
    INDEX
    Explanations

    **airline plane**

    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
     arbitrary
    -0.06
     Felic
    -0.06
    ORT
    -0.06
    anta
    -0.05
    常æĢģ
    -0.05
     Lanc
    -0.05
     Arbitrary
    -0.05
    noi
    -0.05
    æ²³å¸Ĥ
    -0.05
     Conc
    -0.05
    POSITIVE LOGITS
    verg
    0.07
    åĨ³å®ļæĺ¯åIJ¦
    0.05
    ect
    0.05
    ãĤ¯
    0.05
     hol
    0.05
     só
    0.05
    .docs
    0.05
    lion
    0.05
    atamente
    0.05
     ac
    0.05
    Activations Density 0.161%

    No Known Activations