© 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. 9144
    Prev
    Next
    INDEX
    Explanations

    finding or gaining profit

    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°±æĺ¯ä¸Ģ个
    -0.09
    illes
    -0.09
    æľ¬èº«å°±æĺ¯
    -0.09
    åĵªéĩĮ
    -0.09
    éĤ£éĩĮ
    -0.08
    åĽºçĦ¶
    -0.08
    alent
    -0.08
    anic
    -0.08
    渤
    -0.08
    ansk
    -0.08
    POSITIVE LOGITS
    羣æŃ£
    0.15
    æľĢ为
    0.12
    羣æŃ£çļĦ
    0.11
     ÑģобÑģÑĤвенно
    0.11
    æľĢãĤĤ
    0.11
    å¾Ĺ以
    0.10
    人æŃ»äº¡
    0.10
     truly
    0.09
     most
    0.09
    尤为
    0.09
    Activations Density 0.064%

    No Known Activations