© 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. 21962
    Prev
    Next
    INDEX
    Explanations

    code comments or markup

    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
    orary
    -0.06
     ÑĤаÑĢи
    -0.06
     sembl
    -0.06
    ica
    -0.06
     Bons
    -0.06
     pars
    -0.06
    upun
    -0.06
    å·®ä¸įå¤ļäºĨ
    -0.06
    ä¸īè§Ĥ
    -0.06
    orton
    -0.06
    POSITIVE LOGITS
     everyday
    0.06
    ä¸Ģ串
    0.05
    åĨĪ
    0.05
    åİĮ
    0.05
    åıĬæŶå¤ĦçIJĨ
    0.05
    让æķ´ä¸ª
    0.05
    wart
    0.05
    ↵↵
    0.05
     gern
    0.05
     nab
    0.05
    Activations Density 0.014%

    No Known Activations