© 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. 19039
    Prev
    Next
    INDEX
    Explanations

    azoesters, azoospermia, azomethine, azide, azido

    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
    ĥĿ
    -0.07
    volle
    -0.06
     TIMES
    -0.06
    ä¹ŁæĽ´
    -0.06
     اÙĦÙĥÙĦ
    -0.06
    리면
    -0.06
    гÑĢан
    -0.05
     Favor
    -0.05
    综
    -0.05
    лог
    -0.05
    POSITIVE LOGITS
    kest
    0.05
    ...
    0.05
    çıĤ
    0.05
    aight
    0.05
     transfers
    0.05
     Planned
    0.05
    precated
    0.05
    akh
    0.05
    转移
    0.05
    ouch
    0.05
    Activations Density 0.001%

    No Known Activations