© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10414
    Prev
    Next
    INDEX
    Explanations

    malware, virus, microbial contamination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    æijĦ
    -0.20
    alis
    -0.20
    æĭ§
    -0.19
     Oops
    -0.19
    巴士
    -0.19
    .flush
    -0.18
    èģĶåIJĪä¼ļ
    -0.18
    è¢ľ
    -0.17
    utt
    -0.17
    å·©
    -0.17
    POSITIVE LOGITS
    é²ł
    0.22
    çĥŁçģ«
    0.21
    æ¯ĴæĢ§
    0.20
    é£İéĻ©
    0.20
     Trojan
    0.19
     nuisance
    0.19
     Jacqu
    0.18
    ucher
    0.18
    çĸł
    0.18
     Ready
    0.18
    Activations Density 0.005%

    No Known Activations