© 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. 19430
    Prev
    Next
    INDEX
    Explanations

    male / garment / state / games

    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
     essentials
    -0.05
     Essentials
    -0.05
    åĴĮæ°Ķ
    -0.05
    amore
    -0.05
    人ä¹ĭ
    -0.05
    aph
    -0.05
    dotenv
    -0.05
    æŃ£å¼ıçīĪ
    -0.05
    ä¼´
    -0.05
     basics
    -0.05
    POSITIVE LOGITS
    سد
    0.06
    大å±ķ
    0.06
     oportun
    0.06
    èĥĮæĻ¯
    0.05
    zap
    0.05
    tails
    0.05
    寡
    0.05
    פ×Ļ×Ŀ
    0.05
    Õµ
    0.05
    æĥħåĨµè¯´æĺİ
    0.05
    Activations Density 0.016%

    No Known Activations