© 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. 8289
    Prev
    Next
    INDEX
    Explanations

    punctuation and non-latin scripts

    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
    ä¸įåĨį
    -0.10
     Boone
    -0.08
    ä¸įä»ħè¦ģ
    -0.08
    èİ«è¿ĩäºİ
    -0.08
    åĨħå¤ĸ
    -0.08
    ä½ĵ
    -0.08
    ç½ijåıĭè¯Ħ论
    -0.08
    å¥ļ
    -0.08
    æī¹ç¤º
    -0.08
    骸
    -0.08
    POSITIVE LOGITS
    è·ĥ
    0.10
    ific
    0.10
    æĽ´éĢĤåIJĪ
    0.10
    è¿Ļæīįæĺ¯
    0.10
    è¿Īè¿Ľ
    0.09
    çĮĿ
    0.09
    ãģ»ãģĨãģĮ
    0.09
    ÑģÑĥ
    0.09
    åĬ¨æīĭ
    0.09
    åIJİèĢħ
    0.09
    Activations Density 0.106%

    No Known Activations