© 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. 16792
    Prev
    Next
    INDEX
    Explanations

    Apache License Version 2.0

    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
    ett
    -0.06
    ãĥ¼ãĤ¸ãĥ£
    -0.06
    æľ¬æĸĩä¸Ń
    -0.06
    вное
    -0.06
    çļĦ人身
    -0.06
    intr
    -0.06
    adle
    -0.06
    ç¨İæ³ķ
    -0.06
    çĶŁåij½ä¸ŃçļĦ
    -0.05
    é¼»åŃĶ
    -0.05
    POSITIVE LOGITS
    ↵
    0.05
    ев
    0.05
    0.05
    atoi
    0.05
     mÃŃt
    0.05
     Along
    0.05
    Descriptors
    0.05
    avad
    0.05
    èĢĮçĶŁ
    0.05
     beis
    0.05
    Activations Density 0.012%

    No Known Activations