© 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. 20388
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    è¦ĥ
    -0.06
    iston
    -0.06
    çĶ»æ³ķ
    -0.06
    åĨįçĤ¹åĩ»
    -0.06
    ä¸ĢåĪ»
    -0.06
    ueb
    -0.06
    -big
    -0.05
    .ma
    -0.05
    à¸Ľà¸£à¸²à¸ģาร
    -0.05
    Ñģлан
    -0.05
    POSITIVE LOGITS
    åĩºç«Ļ
    0.05
    æģ¶å¿ĥ
    0.05
    ategor
    0.05
    staat
    0.05
    åı¬å¼ĢäºĨ
    0.05
    adet
    0.05
     வி
    0.05
     sat
    0.05
    uci
    0.05
    çľ¼çĿĽ
    0.05
    Activations Density 0.000%

    No Known Activations