© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18616
    Prev
    Next
    INDEX
    Explanations

    citations like [[@B1

    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
    ..
    -0.06
    ...
    -0.05
    test
    -0.05
    åĪ°çļĦ
    -0.05
    ..\
    -0.05
    天
    -0.05
    çİīæłij
    -0.05
    çļĦè¿ĺæĺ¯
    -0.04
    åıĶåıĶ
    -0.04
    è¿ĩ
    -0.04
    POSITIVE LOGITS
    heck
    0.07
     geïn
    0.06
    ØŃÙĬØ©
    0.06
    maÃŁen
    0.06
    deles
    0.06
    бÑĥдÑĮÑĤе
    0.06
    åįķæĸ¹
    0.06
    kowo
    0.06
     ///<
    0.06
    æĴ¥
    0.06
    Activations Density 0.003%

    No Known Activations