© 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. 64094
    Prev
    Next
    INDEX
    Explanations

    check out

    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
    ning
    -0.11
    AGER
    -0.10
    æĪijçŁ¥éģĵ
    -0.09
    è°ĭ
    -0.09
    NING
    -0.09
    éĵ¶
    -0.09
    quet
    -0.08
    åĹij
    -0.08
    acus
    -0.08
     Higgins
    -0.08
    POSITIVE LOGITS
    åIJ¬åIJ¬
    0.10
    é¬ĥ
    0.10
    åİ»çľĭçľĭ
    0.09
     out
    0.09
    åĮ»çĸĹæľºæŀĦ
    0.09
    äºĮæīĭ
    0.09
    æĿ¥çľĭçľĭåIJ§
    0.08
    åİŁæĸĩåľ°åĿĢ
    0.08
    ä¸Ģçľĭ
    0.08
     sức
    0.08
    Activations Density 0.018%

    No Known Activations