© 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. 19261
    Prev
    Next
    INDEX
    Explanations

    printing or print commands

    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
    iya
    -0.05
    ↵
    -0.05
    第ä¸ĢçĻ¾ä¸Ģ
    -0.05
    "
    -0.05
    -0.05
    ../../../
    -0.05
    imson
    -0.05
    .
    -0.05
    åŀĭ
    -0.05
    æĺ¯åIJ¦
    -0.05
    POSITIVE LOGITS
    tings
    0.08
    ждÑĥÑİ
    0.07
    /cop
    0.07
    .isDebugEnabled
    0.07
    (er
    0.07
    linger
    0.07
    erman
    0.07
    ÙħÙĬÙĦ
    0.07
    ëŁŃ
    0.07
    ertos
    0.07
    Activations Density 0.029%

    No Known Activations