© 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. 18162
    Prev
    Next
    INDEX
    Explanations

    explaining riddles or puzzles

    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
    çľĭ
    -0.06
    æĥ³çľĭ
    -0.06
    uns
    -0.05
    ä¸Ģ亮
    -0.05
    æĬĽ
    -0.05
    æĬķ
    -0.05
    ult
    -0.05
    ä¹Łæĥ³
    -0.05
    le
    -0.05
     *
    -0.05
    POSITIVE LOGITS
    imson
    0.06
    acula
    0.06
    erse
    0.06
    æĹ¥å¤ľ
    0.06
    ستÙĩ
    0.06
    adres
    0.06
    ER
    0.06
    åı£ä¸ŃçļĦ
    0.06
    erals
    0.06
    ares
    0.06
    Activations Density 0.002%

    No Known Activations