© 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. 19666
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    unk
    -0.05
     arch
    -0.05
    ÑĨов
    -0.05
    çĦ¶
    -0.05
    ãĥ¼ãĥł
    -0.05
    çľĭä»ĸ
    -0.05
    عاÙĨ
    -0.05
    åIJ¸
    -0.05
    ï¸ı
    -0.05
    át
    -0.05
    POSITIVE LOGITS
    oken
    0.07
    leben
    0.07
    ãģ¦ãĤĤãĤī
    0.06
    _strlen
    0.06
    przed
    0.06
    _texts
    0.06
    é¼İé¼İ
    0.06
    olas
    0.06
    æ¡¥æŀ¶
    0.06
    Represent
    0.06
    Activations Density 0.000%

    No Known Activations