© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40407
    Prev
    Next
    INDEX
    Explanations

    death or fatal outcomes

    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
    Negative Logits
    çĻ¾å®¶
    -0.11
    éĢĢ
    -0.09
    éĢĢå½¹
    -0.09
    ç»ıåİĨ
    -0.09
     Venez
    -0.09
     опÑĭÑĤ
    -0.09
    ä¸Ģ度
    -0.08
     wreak
    -0.08
     retired
    -0.08
    subst
    -0.08
    POSITIVE LOGITS
    èĩ´åij½
    0.10
    è¹Ī
    0.10
    die
    0.09
    ä¸Ģåı¥è¯Ŀ
    0.09
    åĢĴåľ¨
    0.09
    饿
    0.09
    tsy
    0.09
    æµģæĺŁ
    0.09
    due
    0.09
     fatal
    0.09
    Activations Density 0.191%

    No Known Activations