© 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. 52324
    Prev
    Next
    INDEX
    Explanations

    controversial

    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
    å¥łåŁº
    -0.08
    ÑĪе
    -0.08
    追
    -0.08
    åħ±å»º
    -0.08
    åı¯æݧ
    -0.08
    çħ§æĸĻ
    -0.08
    ÙĨØ´
    -0.08
    ä¸įåľ¨ä¹İ
    -0.08
    å¤ĩèĢĥ
    -0.08
    潮湿
    -0.08
    POSITIVE LOGITS
     controversial
    0.19
    äºīè®®
    0.19
     controversy
    0.15
    è´¨çĸij
    0.15
    æľī人说
    0.15
    éģŃåĪ°
    0.14
    è¯Ł
    0.14
    被认为
    0.14
     controversies
    0.13
     critics
    0.13
    Activations Density 0.189%

    No Known Activations