© 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. 20985
    Prev
    Next
    INDEX
    Explanations

    safety equipment and protective gear

    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
    мел
    -0.09
    ä¿İ
    -0.09
    IPP
    -0.09
    -pill
    -0.08
     desn
    -0.08
    пÑĢавлÑı
    -0.08
    ä¸įåĪ©
    -0.08
    Encoder
    -0.08
     Wheeler
    -0.08
    æĭ¾
    -0.08
    POSITIVE LOGITS
    代åĬŀ
    0.11
    åºĨ
    0.10
    éĺ²çģ«
    0.10
    壮
    0.10
    éŀĭ
    0.09
    ç²¾ç¥ŀ
    0.09
    æ¶Īéĺ²
    0.09
    çĬĴ
    0.09
    ä¸įå°ijäºİ
    0.09
    åĪijèѦ
    0.09
    Activations Density 0.138%

    No Known Activations