© 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. 9267
    Prev
    Next
    INDEX
    Explanations

    however

    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
    好åIJĹ
    -0.11
     zwar
    -0.11
    äºİæĺ¯æĪij
    -0.11
    ä½Ĩ她
    -0.11
    åŁİéķĩåĮĸ
    -0.11
    æ¯ĶæĪij
    -0.10
    çĥĤ
    -0.10
    äºİæĺ¯
    -0.09
    éıĸ
    -0.09
    çĦ¶æĺ¯
    -0.09
    POSITIVE LOGITS
    çĶ±äºİ
    0.11
    è¿Ļä¹Łæĺ¯
    0.10
    å®ĥ
    0.10
    大å¤ļæķ°
    0.10
    å½ĵ
    0.09
    åĩ¡æĺ¯
    0.08
    æĪij们è¦ģ
    0.08
    æľīäºĽ
    0.08
    hma
    0.08
    ä»ĸä¹Ł
    0.08
    Activations Density 0.287%

    No Known Activations