© 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. 38820
    Prev
    Next
    INDEX
    Explanations

    drowning and pneumonia

    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
    ories
    -0.10
    åŁł
    -0.09
    è¾ĥ强
    -0.08
     Gregg
    -0.08
    urry
    -0.08
    ì¦Į
    -0.08
    亲åĪĩ
    -0.08
    æĥ®
    -0.08
    èħ°
    -0.08
     Troll
    -0.08
    POSITIVE LOGITS
    äºĨä»ĸçļĦ
    0.10
    æ·¹
    0.09
    æ¶Ĥ
    0.09
    溺
    0.09
    лад
    0.08
    ä¸ĸçķĮç»ıæµİ
    0.08
    潺
    0.08
    Õ¹
    0.08
    éģIJ
    0.08
    mars
    0.08
    Activations Density 0.005%

    No Known Activations