© 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. 21688
    Prev
    Next
    INDEX
    Explanations

    app or application

    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
    z
    -0.05
     rendering
    -0.05
    ader
    -0.05
    try
    -0.05
     ruling
    -0.05
     based
    -0.05
    k
    -0.05
    ba
    -0.05
    åŁºäºİ
    -0.05
    sk
    -0.05
    POSITIVE LOGITS
    ueux
    0.07
    iên
    0.07
    èses
    0.06
    osso
    0.06
    pecia
    0.06
    arters
    0.06
     Mavericks
    0.06
    xmlns
    0.06
    aven
    0.06
    oca
    0.06
    Activations Density 0.061%

    No Known Activations