© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51676
    Prev
    Next
    INDEX
    Explanations

    great companies

    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
    Not in Any Lists

    No Comments

    Negative Logits
     chù
    -0.09
    åIJĪèĤ¥
    -0.08
    以åıĬåħ¶ä»ĸ
    -0.08
    èıĸ
    -0.08
    (end
    -0.08
    æĪĸèĢħåħ¶ä»ĸ
    -0.08
     contrary
    -0.08
    WISE
    -0.08
     end
    -0.08
    éĶº
    -0.08
    POSITIVE LOGITS
    æĽ´æĺ¯
    0.28
    æĽ´ä¸º
    0.17
    æĽ´è¦ģ
    0.16
    尤为
    0.16
    ãģķãĤīãģ«
    0.16
    è¿Ľä¸ĢæŃ¥
    0.15
    æĽ´åĬł
    0.15
     outright
    0.15
    çĶļèĩ³æĺ¯
    0.14
    æĽ´å¤§
    0.14
    Activations Density 0.160%

    No Known Activations