© 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. 51883
    Prev
    Next
    INDEX
    Explanations

    fish and aquatic conservation

    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
    USAGE
    -0.10
    æ¬ł
    -0.09
    ç½ijé¦ĸ页
    -0.09
    åĽļ
    -0.09
     ØŃص
    -0.09
    à¹Ħล
    -0.09
    端åįĪ
    -0.09
    åIJŀ
    -0.09
    inho
    -0.09
     Christie
    -0.08
    POSITIVE LOGITS
    åĪĨæīĭ
    0.09
    æĤ¬å´ĸ
    0.09
    Spoiler
    0.09
     wet
    0.08
    ä¸ĭä¸Ģ代
    0.08
    伪
    0.08
    çIJĨäºĭä¼ļ
    0.08
     Wet
    0.08
    åį¯
    0.08
    æĴ¤ç¦»
    0.08
    Activations Density 0.064%

    No Known Activations