© 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. 22103
    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
     myself
    -0.06
    æĬ±æĬ±
    -0.05
    ç½¹
    -0.05
     {_
    -0.05
    ä¸ĢæĪĺ
    -0.05
    полÑĮ
    -0.05
    plib
    -0.05
    ä¹ĭåĪĹ
    -0.05
    usz
    -0.05
     Ones
    -0.05
    POSITIVE LOGITS
    åįı
    0.06
    å¦ĥ
    0.06
    عÙĬ
    0.06
    ç£Ĭ
    0.06
     kaut
    0.06
    æİ¥è¿ĩ
    0.06
    ancers
    0.06
    äºĪ
    0.06
    عاÙħ
    0.06
    äºĮ人
    0.05
    Activations Density 0.000%

    No Known Activations