© 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. 20951
    Prev
    Next
    INDEX
    Explanations

    artwork, illustration, painting, art contest

    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
    äºĮ个
    -0.05
    otes
    -0.05
    å±±éĩĮ
    -0.05
    带走äºĨ
    -0.05
     Inner
    -0.05
    Inner
    -0.05
    iki
    -0.05
    cesso
    -0.05
    ikon
    -0.05
    ote
    -0.05
    POSITIVE LOGITS
    é¼ĵ楼åĮº
    0.06
    主åĬĽ
    0.06
    abcdefgh
    0.05
    ÑĩеÑĢед
    0.05
    arra
    0.05
    urz
    0.05
     guessed
    0.05
    符
    0.05
    eria
    0.05
    çīĪ
    0.05
    Activations Density 0.003%

    No Known Activations