© 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. 29589
    Prev
    Next
    INDEX
    Explanations

    coming to

    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
    ãĥ¢ãĥİ
    -0.10
    erior
    -0.08
    çݳ
    -0.08
    äºĨåįĬ天
    -0.08
    entlich
    -0.08
    æ¯ķ
    -0.08
    èĩªåıij
    -0.08
    _PHP
    -0.08
    è¢į
    -0.08
    ambi
    -0.08
    POSITIVE LOGITS
    åħ¥é©»
    0.10
    è¿Ľé©»
    0.09
    åħ¥ä½ı
    0.09
    æĦıåij³çĿĢ
    0.08
    åıįå¼¹
    0.08
    æīĺè¿IJ
    0.08
    æĻ®
    0.08
    ä»ħä¾ĽåıĤèĢĥ
    0.08
    inky
    0.08
    ä¼
    0.08
    Activations Density 0.036%

    No Known Activations