© 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. 40347
    Prev
    Next
    INDEX
    Explanations

    storage contents

    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
    åIJįåįķ
    -0.09
    æ·ŀ
    -0.09
    æıIJä¾Ľä¼ĺè´¨
    -0.09
    è´Łæĭħ
    -0.09
    èĦ©
    -0.09
    çĭİ
    -0.09
    赶ä¸Ĭ
    -0.09
    éĺŁä¼į建设
    -0.09
    éªij
    -0.08
    éºĭ
    -0.08
    POSITIVE LOGITS
    çī©åĵģ
    0.18
    æIJ¬
    0.14
    æIJ¬å®¶
    0.13
    æĶ¶æĭ¾
    0.13
    æķ´çIJĨ
    0.13
     items
    0.12
    æĿĤçī©
    0.12
     веÑī
    0.11
    æĶ¶çº³
    0.11
    æIJ¬è¿ģ
    0.11
    Activations Density 0.069%

    No Known Activations