© 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. 29381
    Prev
    Next
    INDEX
    Explanations

    any [noun]

    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
     Rog
    -0.10
    Ñīа
    -0.09
     Dank
    -0.09
    abeth
    -0.09
    _DRV
    -0.09
     backs
    -0.09
     bó
    -0.09
    iltr
    -0.08
    èį·
    -0.08
    çijŀåħ¸
    -0.08
    POSITIVE LOGITS
    ä¸Ģåı·
    0.11
    ä»»ä½ķå½¢å¼ı
    0.11
    åħ¬åĬ¡
    0.10
    åĵªæĢķæĺ¯
    0.09
    éķ¿çĽ¸
    0.09
    å¥
    0.09
    ç¼ģ
    0.09
    éªľ
    0.09
    çĶŃ
    0.08
    æĺ¯æľĢ
    0.08
    Activations Density 0.065%

    No Known Activations