© 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. 12174
    Prev
    Next
    INDEX
    Explanations

    Did you know

    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
    çªĥ
    -0.09
     Pres
    -0.09
    èµ°å¾Ĺ
    -0.09
    shit
    -0.09
    ä¸įè´Ł
    -0.08
    ündig
    -0.08
    ä¾ĿçĦ¶æĺ¯
    -0.08
    ä¸Ģåī¯
    -0.08
    å¿«ä¸ī
    -0.08
    奸
    -0.08
    POSITIVE LOGITS
    åIJ¬è¯´è¿ĩ
    0.15
    说è¿ĩ
    0.15
    注æĦıåĪ°
    0.13
    ãģĹãģŁãģĵãģ¨
    0.12
    è¿ĺè®°å¾Ĺ
    0.12
    äºĨåIJĹ
    0.11
    说äºĨ
    0.11
    æĥ³åĪ°
    0.11
    ä½łçŁ¥éģĵ
    0.11
    æĥ³è¿ĩ
    0.11
    Activations Density 0.023%

    No Known Activations