© 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. 21246
    Prev
    Next
    INDEX
    Explanations

    sides or parties

    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
    .jboss
    -0.10
     Ñģов
    -0.09
    æĺ¯ä»ĸ
    -0.09
     Serg
    -0.09
    éĻĽ
    -0.09
    æĺ
    -0.08
    marked
    -0.08
    USTER
    -0.08
    ä½łä»¥ä¸º
    -0.08
    -chat
    -0.08
    POSITIVE LOGITS
    åıĮæĸ¹
    0.14
     sides
    0.13
    å½ĵäºĭ人
    0.12
     parties
    0.12
    å½ĵäºĭ
    0.12
    ä¸Ģæĸ¹
    0.11
    å¤ļæĸ¹
    0.11
    åIJĦæĸ¹
    0.11
    طرÙģ
    0.10
     ÑģÑĤоÑĢонÑĭ
    0.10
    Activations Density 0.041%

    No Known Activations