© 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. 19685
    Prev
    Next
    INDEX
    Explanations

    beautiful people or model

    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
    åħľ
    -0.06
     determin
    -0.06
    åı¯å¢ŀåĬł
    -0.06
    ä»·
    -0.06
    åºķæ°Ķ
    -0.06
    模å¼ıçļĦ
    -0.05
     encompass
    -0.05
    eneg
    -0.05
    æģķ
    -0.05
    bid
    -0.05
    POSITIVE LOGITS
    istory
    0.06
    ležitost
    0.06
    orsk
    0.06
    erso
    0.05
    ryn
    0.05
    æĬ¢çľ¼
    0.05
    对产åĵģ
    0.05
    ña
    0.05
    uld
    0.05
    sorting
    0.05
    Activations Density 0.001%

    No Known Activations