© 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. 573
    Prev
    Next
    INDEX
    Explanations

    which / whom followed by pronouns

    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
    ä¸įæŃ»
    -0.11
    ippers
    -0.10
    ulas
    -0.10
    æīĢ以说
    -0.10
    åij¼åIJģ
    -0.09
    RowAt
    -0.09
    èł¹
    -0.09
    riad
    -0.09
    åĮĸåIJĪ
    -0.09
    лÑĮн
    -0.09
    POSITIVE LOGITS
    åģļçĶŁæĦı
    0.09
    çĵ¯
    0.08
    æľīåħ³
    0.08
    èĤĩ
    0.08
    æ²¾
    0.08
    èħ°
    0.08
    ä»İäºĭ
    0.08
    iniz
    0.08
     conferred
    0.08
    æľīéĹľ
    0.07
    Activations Density 0.060%

    No Known Activations