© 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. 16569
    Prev
    Next
    INDEX
    Explanations

    wrist and ankle injuries

    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
    aft
    -0.07
    ä¸įæĹ©
    -0.06
    iglio
    -0.06
    auss
    -0.06
    FILE
    -0.06
    illion
    -0.06
    illac
    -0.06
    Archivo
    -0.05
    aes
    -0.05
    fore
    -0.05
    POSITIVE LOGITS
     wrists
    0.07
     ankle
    0.06
    èĦļè¸Ŀ
    0.06
     ankles
    0.06
    кÑĢÑĥ
    0.06
    æĤ¸
    0.06
    yarat
    0.06
     wrist
    0.06
    ients
    0.06
    è¸Ŀ
    0.06
    Activations Density 0.008%

    No Known Activations