© 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. 10946
    Prev
    Next
    INDEX
    Explanations

    cardiac arrest, shock, or failure

    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
    æģ¶
    -0.10
    ureau
    -0.10
    adora
    -0.09
    èĪ¶
    -0.09
    uien
    -0.09
     Tough
    -0.09
    ationToken
    -0.09
    tero
    -0.09
    _startup
    -0.09
    转æĬĺ
    -0.09
    POSITIVE LOGITS
    ç»ıéªĮåĴĮ
    0.10
    inka
    0.10
     fatal
    0.09
     shock
    0.09
    æĦīå¿«
    0.09
    å¿ĥæĦ¿
    0.08
    ä¸ĭ车
    0.08
     OU
    0.08
    éĹŃ
    0.08
     ó
    0.08
    Activations Density 0.076%

    No Known Activations