© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49987
    Prev
    Next
    INDEX
    Explanations

    electrical circuit protection

    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
    yny
    -0.09
    æ¶Īæŀģ
    -0.09
    èĨĬ
    -0.09
    æį·
    -0.09
    åħ«åįģ
    -0.09
    åĭ¢
    -0.09
    åIJ¸éĻĦ
    -0.09
    ä¹Ŀåįģ
    -0.09
    å°ijæķ°
    -0.09
    ç¾ŀ
    -0.09
    POSITIVE LOGITS
    ä¿ĿæĬ¤
    0.11
     protection
    0.10
    年第
    0.10
    æ³»
    0.10
     заÑīиÑĤ
    0.10
    tered
    0.10
    æĶ¾è¿ĩ
    0.10
     Protection
    0.09
     protective
    0.09
    ä¿ĿèŃ·
    0.09
    Activations Density 0.069%

    No Known Activations