© 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. 47599
    Prev
    Next
    INDEX
    Explanations

    disease, infections, molecular methods

    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
    oris
    -0.10
    æ³¼
    -0.10
     unl
    -0.10
    ythe
    -0.09
    ighet
    -0.09
     Souls
    -0.09
    omers
    -0.09
    orrent
    -0.09
    Immediate
    -0.08
    enate
    -0.08
    POSITIVE LOGITS
     rÃłng
    0.09
    åĢ¦
    0.09
    å½Ģ
    0.08
    æĿľåħ°
    0.08
    è¿Ļä¸ĢçĤ¹
    0.08
    亶
    0.08
    atures
    0.08
    rist
    0.08
    伺
    0.08
    ä¼ijæģ¯
    0.08
    Activations Density 0.007%

    No Known Activations