© 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. 27665
    Prev
    Next
    INDEX
    Explanations

    contracting illness or contamination

    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
    ä¸į失
    -0.11
    ä¸įå¿į
    -0.10
    åĢ¾
    -0.10
    èĩĬ
    -0.09
    丰满
    -0.09
    å¤ļåĬŁèĥ½
    -0.09
    åĩºåĬ¨
    -0.09
     drowning
    -0.09
     drown
    -0.09
    è¡Ģèħ¥
    -0.09
    POSITIVE LOGITS
    ä¼łæĴŃ
    0.13
    æĦŁæŁĵ
    0.11
    æĬĹä½ĵ
    0.10
     infection
    0.10
    åħ¬åħ±åį«çĶŁ
    0.10
    åªĴä»ĭ
    0.10
    çĶŁçĹħ
    0.09
    åħ±çĶŁ
    0.09
    æħ°éĹ®
    0.09
    éĺ²æݧ
    0.09
    Activations Density 0.075%

    No Known Activations