© 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. 18096
    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
     ΣÏįμÏĨÏīνα
    -0.06
    urent
    -0.06
    åıĪå¦Ĥ
    -0.06
     maga
    -0.06
    ç«ŀ
    -0.06
    piegel
    -0.06
     stamped
    -0.06
    ανε
    -0.06
    sembly
    -0.06
    ury
    -0.06
    POSITIVE LOGITS
    åı¯æģ¶
    0.05
    æĺİæĺ¾æĶ¹åĸĦ
    0.05
    ä¸Ģ缮
    0.05
    çİ¥
    0.05
    ä¸ĢæīĢ
    0.05
    æĺİæĺ¾
    0.05
     Aus
    0.05
     altern
    0.04
    æľīæĺİæĺ¾
    0.04
     vorbe
    0.04
    Activations Density 0.000%

    No Known Activations