© 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. 29526
    Prev
    Next
    INDEX
    Explanations

    electrical conduit and utility services

    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
    æĬĽ
    -0.10
    ç¼´è´¹
    -0.10
    æıĸ
    -0.09
    ç»Ŀ
    -0.09
    èIJİ
    -0.09
    rap
    -0.08
    =index
    -0.08
    èĥĻ
    -0.08
    çŃ¹èµĦ
    -0.08
    æİĩ
    -0.08
    POSITIVE LOGITS
    æĶ¯æŀ¶
    0.10
    å§ĭ
    0.09
     lou
    0.09
    éĴ´
    0.09
    æĢ»è§īå¾Ĺ
    0.09
    èĮİ
    0.09
     wsz
    0.08
     Bik
    0.08
    abay
    0.08
     ÑģвеÑĤ
    0.08
    Activations Density 0.047%

    No Known Activations