© 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. 64002
    Prev
    Next
    INDEX
    Explanations

    RT/row/kernel/Lens/Bible/Tribe/boarding

    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
    ç»ŀ
    -0.11
    ENU
    -0.09
    æĥ³èµ·æĿ¥
    -0.09
    åħ¬åŃIJ
    -0.09
    _IOC
    -0.09
    пеÑĩ
    -0.08
    acro
    -0.08
    cio
    -0.08
    ä¸įåı¯æĢĿ
    -0.08
    æĪ´ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    ä¸ĵçĶ¨
    0.09
    éĻ¤å¤ĸ
    0.08
    çī¹æľīçļĦ
    0.08
    -inspired
    0.08
    ä¸ĵ项
    0.08
    çĭ¬çī¹çļĦ
    0.08
    -themed
    0.07
    ç©
    0.07
    æ¦Ķ
    0.07
     bl
    0.07
    Activations Density 0.823%

    No Known Activations