© 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. 20018
    Prev
    Next
    INDEX
    Explanations

    computing power and resources

    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
    kof
    -0.05
    itse
    -0.05
    注åħ¥
    -0.05
     adaptation
    -0.05
     Marino
    -0.05
    ä¼łåħ¥
    -0.05
    orough
    -0.05
    æİı
    -0.05
    åŀĤ
    -0.05
    cente
    -0.05
    POSITIVE LOGITS
    mey
    0.06
     chỼp
    0.06
    +i
    0.06
    å¤ļåı°
    0.06
    æķ°æį®ç»Łè®¡
    0.06
     nights
    0.06
     råd
    0.06
     trÃłng
    0.06
    ÛĮاÙĨ
    0.06
     Ø´Ú©ÙĨ
    0.06
    Activations Density 0.004%

    No Known Activations