© 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. 22598
    Prev
    Next
    INDEX
    Explanations

    schema names, same structure

    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
    Negative Logits
    鼷åIJĮ
    -0.07
    erber
    -0.06
    çĽ¸ä¼¼
    -0.06
    åıªèĥ½çĶ¨
    -0.05
    race
    -0.05
    åħ±æĢ§
    -0.05
    鼷æĸ¯
    -0.05
    çĭ¬ä¸ĢæĹłäºĮçļĦ
    -0.05
     Universal
    -0.05
    bserv
    -0.05
    POSITIVE LOGITS
    èĦ±
    0.06
    è¯ķè¯ķ
    0.06
     reg
    0.05
     ض
    0.05
    ew
    0.05
    ETS
    0.05
    بع
    0.05
    ÑĤÑİ
    0.05
    wujud
    0.05
     chance
    0.05
    Activations Density 0.056%

    No Known Activations