© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 24345
    Prev
    Next
    INDEX
    Explanations

    secret agents and spies

    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
    Negative Logits
    æ¸ħæĻ¨
    -0.10
    æĶ¾è¿ĩ
    -0.10
    æļ´åĬĽ
    -0.10
    æ§
    -0.09
     Violence
    -0.09
    customize
    -0.09
    é¾ĩ
    -0.09
    å°ıçĶ·åŃ©
    -0.09
    slashes
    -0.09
    éĺĥ
    -0.09
    POSITIVE LOGITS
    ugin
    0.10
    è°į
    0.09
     spy
    0.09
    æĥħåł±
    0.08
    åĻ¨æĿIJ
    0.08
    ç´¯
    0.08
    çªĥ
    0.08
    æĥħæĬ¥
    0.08
     pressure
    0.08
    iro
    0.08
    Activations Density 0.047%

    No Known Activations