© 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. 12308
    Prev
    Next
    INDEX
    Explanations

    mexico or mexican

    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¸ħ代
    -0.09
    uala
    -0.09
    建çŃijçī©
    -0.09
     Gos
    -0.09
     Hamp
    -0.09
     далÑĮ
    -0.08
     Gover
    -0.08
     captive
    -0.08
    ãĤ°ãĥ«
    -0.08
    é«ĺåİĭ
    -0.08
    POSITIVE LOGITS
    æ·Į
    0.10
    ä½ľæĸĩ
    0.09
    zik
    0.09
    odyn
    0.09
    çĤ·
    0.09
     sát
    0.09
    忤
    0.09
     marty
    0.09
    çĭĻåĩ»
    0.08
    æŃĮæīĭ
    0.08
    Activations Density 0.040%

    No Known Activations