© 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. 22580
    Prev
    Next
    INDEX
    Explanations

    code comments and programming keywords

    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
    æĹłçĸij
    -0.05
     accompanying
    -0.05
    à§Ī
    -0.05
    izan
    -0.05
     still
    -0.05
    ings
    -0.05
    -request
    -0.05
    éĹ´
    -0.05
     id
    -0.05
    éĿŀ
    -0.05
    POSITIVE LOGITS
    ìĬµ
    0.07
    antha
    0.06
    à¹ĩ
    0.06
    å½ĵå¿ĥ
    0.06
     Rodrig
    0.06
    ä¸İæŶ
    0.06
    ionar
    0.06
    举æīĭ
    0.05
    ве
    0.05
    ارÙĩ
    0.05
    Activations Density 0.001%

    No Known Activations