© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22231
    Prev
    Next
    INDEX
    Explanations

    structure elucidation and identification

    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
    Not in Any Lists

    No Comments

    Negative Logits
     tweeted
    -0.06
    代
    -0.06
    ÛĮشاÙĨ
    -0.06
    veiller
    -0.06
    迹
    -0.06
    æĬ¥å¤į
    -0.06
    wór
    -0.06
    ạnh
    -0.06
     акÑĤиви
    -0.06
    upy
    -0.05
    POSITIVE LOGITS
    为éĩį
    0.06
    为ä¸Ń
    0.06
    解æĥij
    0.06
    æĹłåıĮ
    0.06
    æĪIJæĸ°
    0.06
     elucid
    0.05
     definit
    0.05
     decipher
    0.05
    æľīæĸ°
    0.05
     kr
    0.05
    Activations Density 0.394%

    No Known Activations