© 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. 22453
    Prev
    Next
    INDEX
    Explanations

    numbers or 'design' after 'the'

    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
    mpl
    -0.06
    éĿ¢æĹł
    -0.06
    æĹł
    -0.05
     messenger
    -0.05
    å¹³åı°åĴĮ
    -0.05
    .org
    -0.05
    æĺ¯åĶ¯ä¸Ģ
    -0.05
    åĪ¶çļĦ
    -0.05
    å¹³åı°çļĦ
    -0.05
    messer
    -0.05
    POSITIVE LOGITS
    iÄħc
    0.07
    eler
    0.06
    èĢ½
    0.06
    brook
    0.06
     иÑĤогам
    0.06
    kund
    0.06
    æįŁ
    0.06
    åħ¶èº«
    0.05
    å·²ç»ıå°Ĩ
    0.05
    åģľ
    0.05
    Activations Density 0.003%

    No Known Activations