© 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. 18022
    Prev
    Next
    INDEX
    Explanations

    production-ready development

    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
    sons
    -0.06
    ized
    -0.06
    ç¼ķ
    -0.05
    urred
    -0.05
    å°Ķçī¹
    -0.05
    sson
    -0.05
    æķĪæŀľæĽ´å¥½
    -0.05
     Ñģамим
    -0.05
    epar
    -0.05
     renderItem
    -0.05
    POSITIVE LOGITS
     Satur
    0.05
    atanya
    0.05
    ânt
    0.05
     satur
    0.05
    رÙĪØŃ
    0.05
    edly
    0.05
    é¦
    0.05
     invo
    0.05
     Zip
    0.05
     Burl
    0.05
    Activations Density 0.003%

    No Known Activations