© 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. 19474
    Prev
    Next
    INDEX
    Explanations

    examine, examination, analyzing

    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
    عÙĪØ©
    -0.07
    ếm
    -0.07
    chtet
    -0.07
    echt
    -0.07
    ummy
    -0.06
    åĥıä½ł
    -0.06
    æ°£
    -0.06
     sure
    -0.06
    ktan
    -0.06
     ÙħÙĪاÙĤ
    -0.06
    POSITIVE LOGITS
    缸è¾ħ缸æĪIJ
    0.06
    er
    0.06
    ÙĬزة
    0.05
    alysis
    0.05
    ä¸ŃåĽ½åħ±äº§åħļæĪIJç«ĭ
    0.05
    ultiply
    0.05
    alah
    0.05
    apult
    0.05
    -quarters
    0.05
    åĴĮçIJĨ解
    0.05
    Activations Density 0.027%

    No Known Activations