© 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. 21329
    Prev
    Next
    INDEX
    Explanations

    working memory

    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
    ä¸ĭæĮ«
    -0.06
    æĪIJå¥Ĺ
    -0.06
    eness
    -0.05
    roc
    -0.05
    å°ıé¢ĺ
    -0.05
    ä¸įæĢ¥
    -0.05
    chine
    -0.05
    LOC
    -0.05
    SP
    -0.05
    éĺ²å°ĺ
    -0.05
    POSITIVE LOGITS
    åĨįæİ¥
    0.06
    å¿ħ
    0.06
    ingi
    0.05
    ace
    0.05
    veil
    0.05
    acia
    0.05
    社ä¼ļåĮĸ
    0.05
    åĩ¡
    0.05
    abella
    0.05
    eram
    0.05
    Activations Density 0.003%

    No Known Activations