© 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. 16732
    Prev
    Next
    INDEX
    Explanations

    web technologies (html, css, javascript)

    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
     om
    -0.06
    åĽłæŃ¤åľ¨
    -0.06
    andr
    -0.06
    mand
    -0.06
    acon
    -0.05
    端çļĦ
    -0.05
    ailleurs
    -0.05
     gal
    -0.05
    ark
    -0.05
    端
    -0.05
    POSITIVE LOGITS
    æ·Ģ
    0.06
    æ³¢
    0.06
     erity
    0.06
    ika
    0.05
    æĶ¯æµģ
    0.05
     malu
    0.05
    åħ¨èµĦ
    0.05
    wyn
    0.05
    wai
    0.05
    лÑĥÑĩ
    0.05
    Activations Density 0.004%

    No Known Activations