© 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. 36994
    Prev
    Next
    INDEX
    Explanations

    acupuncture

    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
    AREN
    -0.11
    кÑĤ
    -0.10
    转弯
    -0.10
    egot
    -0.09
    qualification
    -0.09
    æ¦Ĩ
    -0.09
    âĿ®
    -0.09
     ÑĢеÑģÑĤ
    -0.08
    æįİ
    -0.08
    è½®
    -0.08
    POSITIVE LOGITS
    ç©´ä½į
    0.11
    å¾ģ
    0.10
    ç©´
    0.10
     acupuncture
    0.09
    å¾µ
    0.09
    гаÑĢ
    0.09
     Frid
    0.09
    ä¸İåIJ¦
    0.08
    Licensed
    0.08
    å¾ĭ
    0.08
    Activations Density 0.059%

    No Known Activations