© 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. 12331
    Prev
    Next
    INDEX
    Explanations

    home insurance and rebuilding

    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
    çķ´
    -0.12
    æĻĸ
    -0.09
     transpose
    -0.08
    ä¸ķ
    -0.08
    è¿ĺåľ¨
    -0.08
    纡
    -0.08
    æµ·æĬ¥
    -0.08
    igen
    -0.08
    æ¡Ī
    -0.08
    (factory
    -0.08
    POSITIVE LOGITS
    çĨı
    0.12
    çģ¾å®³
    0.12
    åıĹçģ¾
    0.12
    åľ°éľĩ
    0.12
     earthquake
    0.11
    çģ¾éļ¾
    0.11
    大çģ«
    0.11
    汶å·Ŀ
    0.11
    æĪIJé¾Ļ
    0.11
    æĬĹéľĩ
    0.11
    Activations Density 0.081%

    No Known Activations