© 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. 17702
    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
    angelo
    -0.05
    æĸ¯é¡¿
    -0.05
     Stein
    -0.05
    stein
    -0.05
    entic
    -0.05
     Wouldn
    -0.05
    该软件
    -0.05
     ÙħعÙĩÙħ
    -0.05
    åħ¨éĿ¢ä»İ严治åħļ
    -0.05
     Best
    -0.05
    POSITIVE LOGITS
    ean
    0.06
    å°½
    0.06
     Deleg
    0.06
    емо
    0.06
     zade
    0.06
    |[
    0.06
     Viz
    0.06
    ãĤ¾
    0.05
    人士表示
    0.05
    ees
    0.05
    Activations Density 0.000%

    No Known Activations