© 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. 16828
    Prev
    Next
    INDEX
    Explanations

    medical healthcare industry

    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
    Not in Any Lists

    No Comments

    Negative Logits
    -0.06
    ↵
    -0.06
    T
    -0.05
    Âł
    -0.05
    ...
    -0.05
     Vol
    -0.05
     Tre
    -0.05
    e
    -0.05
     cast
    -0.05
     I
    -0.05
    POSITIVE LOGITS
    模å¼ıä¸Ń
    0.08
    antul
    0.07
    æĶ¶äºİ
    0.07
    éĢļçŁ¥æĪij
    0.07
     mancan
    0.07
     gastron
    0.07
     kira
    0.07
     potrai
    0.07
    adurch
    0.07
    avera
    0.07
    Activations Density 0.011%

    No Known Activations