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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19667
    Prev
    Next
    INDEX
    Explanations

    compiling and building code

    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
     plain
    -0.05
    iett
    -0.05
    ai
    -0.05
    æľ¬äººçļĦ
    -0.05
    主çļĦ
    -0.04
     itself
    -0.04
    â
    -0.04
     Survey
    -0.04
    th
    -0.04
     themselves
    -0.04
    POSITIVE LOGITS
    åĤ¨
    0.08
    pati
    0.07
    ebilecek
    0.07
    çŀ»
    0.06
    人寿
    0.06
    noon
    0.06
    slick
    0.06
    -reply
    0.06
     grosses
    0.06
    ministro
    0.06
    Activations Density 0.020%

    No Known Activations