© 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. 16562
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

    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
    é¦
    -0.06
    åĴĮæ°Ķ
    -0.06
    yny
    -0.06
    tris
    -0.06
    quiet
    -0.06
    cep
    -0.06
    ä¸įå¹³
    -0.06
    è´¤
    -0.05
     considéra
    -0.05
    trin
    -0.05
    POSITIVE LOGITS
     Chancen
    0.05
    ë¶Ģ
    0.05
    çº¢ç´ł
    0.05
    æ¯ıä¸Ģ份
    0.05
    alian
    0.05
    igital
    0.05
    canf
    0.05
    ablish
    0.04
     chubby
    0.04
     برگ
    0.04
    Activations Density 0.032%

    No Known Activations