© 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. 22402
    Prev
    Next
    INDEX
    Explanations

    drug administration or condition

    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
    osl
    -0.06
    ä¹ĭæ¯į
    -0.06
    ritt
    -0.05
    å½
    -0.05
    å¿ĥäºĨ
    -0.05
    ä¹ĭä¸ĢçļĦ
    -0.05
    æī¿æĭħèµĶåģ¿è´£ä»»
    -0.05
    ä¸ĸçļĦ
    -0.05
    ä½Ĩæĺ¯ä¸Ģ
    -0.05
    ä¹ĭç¾İ
    -0.05
    POSITIVE LOGITS
    usual
    0.06
    éĺ³åħīä¸ĭ
    0.06
    icals
    0.06
    ype
    0.06
    ime
    0.05
    upan
    0.05
    Äħ
    0.05
     taste
    0.05
     usual
    0.05
    itch
    0.05
    Activations Density 0.192%

    No Known Activations