© 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. 49892
    Prev
    Next
    INDEX
    Explanations

    medical complications and procedures

    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
    enance
    -0.09
    åľī
    -0.09
    æĭ¾
    -0.09
    è¤ĵ
    -0.09
    峪
    -0.08
    çĿ£ä¿ĥ
    -0.08
    åĨįéĢł
    -0.08
    éĦĻ
    -0.08
    InBackground
    -0.08
    鸽
    -0.08
    POSITIVE LOGITS
    åĩĨ
    0.10
    éĴĪ
    0.10
    éķĬ
    0.09
    温æŁĶ
    0.09
    éĩĿ
    0.09
    åIJ¸åıĸ
    0.09
    åĮ»æĬ¤äººåijĺ
    0.09
    桨
    0.08
    æĪIJåĬŁçİĩ
    0.08
    åĩºè·¯
    0.08
    Activations Density 0.266%

    No Known Activations