© 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. 21468
    Prev
    Next
    INDEX
    Explanations

    vegetables and plant parts

    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
    eren
    -0.07
    unate
    -0.06
    vem
    -0.06
    uset
    -0.06
    æ´»çĶ¨
    -0.06
    pagen
    -0.06
    remos
    -0.06
    èŀ
    -0.06
     ÙħÙĨد
    -0.05
    protect
    -0.05
    POSITIVE LOGITS
     Zwie
    0.06
     berk
    0.06
    ÛĮÙĩ
    0.05
    edBy
    0.05
    uela
    0.05
    UND
    0.05
    auge
    0.05
    åd
    0.05
    /os
    0.05
    æİĸ
    0.05
    Activations Density 0.001%

    No Known Activations