© 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. 16790
    Prev
    Next
    INDEX
    Explanations

    contender or contend

    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
    ening
    -0.10
    uen
    -0.10
     ply
    -0.09
    客åķĨ
    -0.08
    æĤ¨åı¯ä»¥
    -0.08
    ÙĩÙĦ
    -0.08
    çĹ¼
    -0.08
    Powered
    -0.08
     Ply
    -0.08
    ä¸įæĽ¾
    -0.08
    POSITIVE LOGITS
    amp
    0.10
    rous
    0.09
    بÙĪ
    0.09
    adera
    0.09
    mere
    0.09
    borg
    0.08
    nable
    0.08
    itor
    0.08
    reation
    0.08
    ä¹ĭä½ľ
    0.08
    Activations Density 0.003%

    No Known Activations