© 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. 19722
    Prev
    Next
    INDEX
    Explanations

    hiring candidates or services

    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
    夷
    -0.06
    endu
    -0.06
    éķ¿è¿ľ
    -0.06
    ลัà¸ļ
    -0.06
     Attendance
    -0.06
    clud
    -0.06
    åĬĽäºī
    -0.06
    æĺł
    -0.05
    amente
    -0.05
    à¸įา
    -0.05
    POSITIVE LOGITS
    lib
    0.05
    trie
    0.05
    Âł
    0.05
    
    0.05
    iken
    0.05
    inhos
    0.05
    éĩĮéĿ¢æľī
    0.05
    trit
    0.05
    à§įতà§ģ
    0.05
     Ward
    0.05
    Activations Density 0.187%

    No Known Activations