© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20876
    Prev
    Next
    INDEX
    Explanations

    network protocol stack

    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
    round
    -0.07
    .hasOwnProperty
    -0.06
     round
    -0.06
    ä¸¥æł¼æĮīçħ§
    -0.06
    ters
    -0.06
     Round
    -0.06
    .RelativeLayout
    -0.06
    ovin
    -0.06
    سÙĦÙħ
    -0.05
    migration
    -0.05
    POSITIVE LOGITS
    eded
    0.06
    æĺ¯åĪĨ
    0.06
    ober
    0.05
     Envir
    0.05
    ede
    0.05
    riet
    0.05
    åĽ¢èģļ
    0.05
    æį®
    0.05
    sce
    0.05
    Ori
    0.05
    Activations Density 0.011%

    No Known Activations