© 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. 19493
    Prev
    Next
    INDEX
    Explanations

    URLs, especially github

    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
    et
    -0.05
    çĸı
    -0.05
    顺
    -0.05
    åıijæĮ¥
    -0.05
     SAS
    -0.05
     Nav
    -0.05
    æĥħ
    -0.05
    èĥĮ
    -0.05
    cond
    -0.05
     const
    -0.05
    POSITIVE LOGITS
    ervi
    0.07
     hype
    0.07
    æĪIJæľ¬é«ĺ
    0.06
    åѵåĮĸåĻ¨
    0.06
    ваÑĤ
    0.06
    êµīìŀ¥
    0.06
    çģ«çĤ¬
    0.06
    é¢Ĩ涨
    0.06
     buzz
    0.06
    å¾Īå¤ļçļĦ
    0.06
    Activations Density 0.019%

    No Known Activations