© 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. 24280
    Prev
    Next
    INDEX
    Explanations

    ACH payments and automated clearing house

    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¸Ģçľĭ
    -0.09
    åħ¬åijĬ
    -0.09
     incest
    -0.09
    äºĶçĻ¾
    -0.09
    æĥħ人
    -0.09
    é±¼
    -0.09
    izz
    -0.09
    寤
    -0.09
    è®´
    -0.08
    arters
    -0.08
    POSITIVE LOGITS
    æłı
    0.09
    conti
    0.09
     automatic
    0.09
    Inst
    0.09
    å°¾
    0.09
    å¤ļå¹´çļĦ
    0.09
    çļĦ好å¤Ħ
    0.09
     Inst
    0.08
    èĩªåĬ¨
    0.08
    æłı缮
    0.08
    Activations Density 0.090%

    No Known Activations