© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16777
    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
    Negative Logits
    æŁ´
    -0.06
    aines
    -0.06
    frage
    -0.05
    vious
    -0.05
    ä¸Ģæĸ¹çļĦ
    -0.05
     мимо
    -0.05
    ail
    -0.05
    ARC
    -0.05
     ass
    -0.05
    é£İåĴĮ
    -0.05
    POSITIVE LOGITS
    符
    0.07
    çľĭä¸į
    0.06
    боÑĩ
    0.05
    ieni
    0.05
    çĥĪ
    0.05
     Mohamm
    0.05
    åIJĦåľ°çļĦ
    0.05
    çļĦ人æĿ¥è¯´
    0.05
    nö
    0.05
    çĶ¨è¿ĩ
    0.05
    Activations Density 0.000%

    No Known Activations