© 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. 19697
    Prev
    Next
    INDEX
    Explanations

    regex patterns and code delimiters

    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
    omia
    -0.05
    çħ§
    -0.05
    ouvrez
    -0.05
    ä¸įè¿ĩè¿Ļ
    -0.05
    üb
    -0.05
    溪éķĩ
    -0.05
    ival
    -0.05
    ä¸Ĭå½ĵ
    -0.05
    alen
    -0.05
    à¸ĸ
    -0.05
    POSITIVE LOGITS
    /down
    0.07
    ä¹ħçļĦ
    0.06
    som
    0.06
    æľ¬å±±
    0.05
    keiten
    0.05
    othi
    0.05
    /disable
    0.05
    /column
    0.05
    å¾Ĺå¤ļ
    0.05
    /left
    0.05
    Activations Density 0.004%

    No Known Activations