© 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. 29400
    Prev
    Next
    INDEX
    Explanations

    critical condition, death, rehabilitation, disabled, life-threatening

    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
     поÑģл
    -0.09
    åħħ
    -0.09
    åĶ®
    -0.09
    å©ļ
    -0.08
    æĪIJçĨŁçļĦ
    -0.08
    ignon
    -0.08
    ä½ķå¿ħ
    -0.08
     Cul
    -0.08
    åĨł
    -0.08
    æ¸ħæ°´
    -0.08
    POSITIVE LOGITS
    Shock
    0.09
     recovery
    0.09
     reconstruct
    0.09
    ä½ıéĻ¢
    0.09
    æıĴ
    0.09
    éĩį伤
    0.09
    æķijæ²»
    0.09
     survivor
    0.09
    åĪĽ
    0.09
    念
    0.09
    Activations Density 0.086%

    No Known Activations