© 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. 9232
    Prev
    Next
    INDEX
    Explanations

    agreement contracts between entities

    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
    ossa
    -0.10
    quet
    -0.10
    满æĢĢ
    -0.10
    gne
    -0.10
    çļĦåĨ³å¿ĥ
    -0.09
    èĦ±è´«
    -0.09
    æĽ´å¤ļ精彩
    -0.09
     Vend
    -0.09
    æ´ĭ
    -0.09
    onne
    -0.09
    POSITIVE LOGITS
     Ñģог
    0.10
    åįıè®®
    0.10
     agreements
    0.10
    笨
    0.10
    让èĩªå·±
    0.10
    åIJĪä½ľåįıè®®
    0.09
     agreement
    0.09
    æĹ©æĻļ
    0.09
    åįıå®ļ
    0.09
    tent
    0.09
    Activations Density 0.146%

    No Known Activations