© 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. 29378
    Prev
    Next
    INDEX
    Explanations

    anywhere else in the world

    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
    ä¸įåłª
    -0.09
    æİ¥åĬĽ
    -0.08
     Donovan
    -0.08
    æľīä¸Ģä½į
    -0.08
    æľ¬ç«Ļ
    -0.08
    çĶ°éĩİ
    -0.08
    表åĨ³
    -0.08
    acus
    -0.08
    æľ¬æĿ¥å°±
    -0.08
    WithPath
    -0.08
    POSITIVE LOGITS
    çĭ¬ä¸ĢæĹłäºĮ
    0.14
    çĭ¬çī¹çļĦ
    0.13
     nowhere
    0.12
     elsewhere
    0.12
     anywhere
    0.12
    çĭ¬åħ·
    0.12
    çĭ¬æľīçļĦ
    0.12
    Anywhere
    0.10
    çī¹æ®ĬçļĦ
    0.10
    çļĦçĭ¬çī¹
    0.10
    Activations Density 0.033%

    No Known Activations