© 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. 22633
    Prev
    Next
    INDEX
    Explanations

    medals, degree, prices, laptops, Richard

    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
    onte
    -0.06
    æĦı
    -0.05
     babe
    -0.05
    个éĹ®é¢ĺ
    -0.05
    adhan
    -0.05
    алÑĮ
    -0.05
    Ups
    -0.05
    计
    -0.05
    ibble
    -0.05
    arem
    -0.05
    POSITIVE LOGITS
    eenth
    0.06
    éĤ£é¢Ĺ
    0.06
    ç»ı审çIJĨ
    0.06
     Acting
    0.06
    fordert
    0.06
    ÙĨاس
    0.06
    annah
    0.06
    uration
    0.06
    ãģ£ãģ¦ãģ¿ãģ¾ãģĹãģŁ
    0.06
    forth
    0.06
    Activations Density 0.043%

    No Known Activations