© 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. 19626
    Prev
    Next
    INDEX
    Explanations

    state of the art

    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
    amore
    -0.06
    延éķ¿
    -0.05
    åĪļ
    -0.05
     pie
    -0.05
    ç²¾ç¥ŀçĹħ
    -0.05
    ersen
    -0.05
    æļĤæŶ
    -0.05
     bud
    -0.05
    çļĦåIJĮæŶ
    -0.05
    uras
    -0.05
    POSITIVE LOGITS
    oth
    0.07
     Declaration
    0.06
     declaration
    0.06
     Definitions
    0.06
     dépl
    0.06
    ä¸įèĥľ
    0.06
     definition
    0.06
    ..)
    0.05
    _subject
    0.05
    topic
    0.05
    Activations Density 0.001%

    No Known Activations