© 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. 40312
    Prev
    Next
    INDEX
    Explanations

    asking where

    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
    aul
    -0.10
    éĿłè¿ij
    -0.10
    egis
    -0.09
     Spears
    -0.09
    äºĶåĽĽ
    -0.08
     bah
    -0.08
    cken
    -0.08
     tik
    -0.08
     Tik
    -0.08
    å®Ľå¦Ĥ
    -0.08
    POSITIVE LOGITS
    æĤ²è§Ĥ
    0.10
    BREAK
    0.09
    è¿Ļ份
    0.09
    磼
    0.09
    èĩªæĿ¥
    0.09
    强大çļĦ
    0.09
    åIJĦ个çݯèĬĤ
    0.09
    á»įng
    0.08
    çļĦ帮åĬ©
    0.08
    éĮ¯
    0.08
    Activations Density 0.039%

    No Known Activations