© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19466
    Prev
    Next
    INDEX
    Explanations

    Python code, models, and database definitions

    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
    èĥľ
    -0.06
    à¸Ńยà¹Īาà¸ĩà¹Ħร
    -0.05
    Âł
    -0.05
    éļĨ
    -0.05
    ä¸Ģä½ĵåĮĸ
    -0.05
    æŃ¢
    -0.05
    绣
    -0.05
    veld
    -0.05
     stead
    -0.05
    å¤ļå°ij
    -0.05
    POSITIVE LOGITS
    нева
    0.06
    ensibly
    0.06
    âĢ¦the
    0.06
    trop
    0.06
     Inizi
    0.06
    æĸĩåĵ²
    0.06
    å±ħçĦ¶æĺ¯
    0.06
     Newly
    0.06
    ä¸ºæł¸å¿ĥçļĦåħļä¸Ń央
    0.05
    synthesize
    0.05
    Activations Density 0.001%

    No Known Activations