© 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. 16693
    Prev
    Next
    INDEX
    Explanations

    code structure

    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
    ä¸Ģå®ļ
    -0.06
    Âł
    -0.06
    urop
    -0.05
     g
    -0.05
    -
    -0.05
     altern
    -0.05
    Ä
    -0.05
    ixin
    -0.05
    æĺ¯æľĢ
    -0.05
     tro
    -0.05
    POSITIVE LOGITS
    jala
    0.07
    jeti
    0.07
    joj
    0.07
     dijer
    0.06
    ело
    0.06
    achter
    0.06
     Ñħоле
    0.06
    اÙĦات
    0.06
    عÙĬ
    0.06
     tweeted
    0.06
    Activations Density 0.023%

    No Known Activations