© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27429
    Prev
    Next
    INDEX
    Explanations

    brain injury trauma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    åŁĴ
    -0.10
    ÙĬÙĨا
    -0.10
    practice
    -0.09
    åºĹåĨħ
    -0.09
    èµĽ
    -0.09
    åĩ«
    -0.09
    è°¶
    -0.09
    vara
    -0.09
    ä¸įåĬ¨
    -0.09
    abar
    -0.09
    POSITIVE LOGITS
    åĮ¡
    0.08
    Ear
    0.08
    IFIER
    0.08
    è·³åĩº
    0.08
     oui
    0.08
    è¡Į车
    0.08
    ared
    0.07
    ãĤ¤ãĥ¤
    0.07
    ium
    0.07
    ç£ĭåķĨ
    0.07
    Activations Density 0.054%

    No Known Activations