© 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. 19423
    Prev
    Next
    INDEX
    Explanations

    punctuation and grouping symbols

    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
    arca
    -0.06
    opan
    -0.06
    oyer
    -0.06
    ä¸Ī
    -0.06
    ä¼łäºº
    -0.06
     afhankelijk
    -0.05
    Äħtek
    -0.05
    ä¸įèµ·
    -0.05
    ulum
    -0.05
    writes
    -0.05
    POSITIVE LOGITS
    صة
    0.05
    }'.
    0.05
    zion
    0.05
    eleg
    0.05
    .||
    0.05
    isty
    0.05
    æľª
    0.05
    ien
    0.05
    人士
    0.05
    å·²ä¹ħçļĦ
    0.05
    Activations Density 0.002%

    No Known Activations