© 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. 52234
    Prev
    Next
    INDEX
    Explanations

    enumeration of items

    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
    è¿ĺä¸įæĺ¯
    -0.09
     racks
    -0.09
     Boone
    -0.09
    кÑģ
    -0.09
    沮丧
    -0.09
    è¿ĺä¸į
    -0.09
    è¿Ļæīį
    -0.08
    æīįèĥ½å¤Ł
    -0.08
    ohn
    -0.08
    crest
    -0.08
    POSITIVE LOGITS
    尤为
    0.11
    为代表
    0.10
    åľ¨è¿Ļæĸ¹éĿ¢
    0.10
    è¿Ļç±»
    0.10
    è¿Ļä¸Ģ
    0.09
    æѤ类
    0.09
    è¿Ļåıª
    0.09
    ä¸įéĶĻ
    0.09
    åīįèĢħ
    0.09
    æħķ
    0.09
    Activations Density 0.348%

    No Known Activations