© 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. 24116
    Prev
    Next
    INDEX
    Explanations

    accounting and auditing services

    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
    anches
    -0.10
    人群
    -0.10
    éĿłè°±
    -0.09
    åħĭåĪ¶
    -0.09
    æĶ¿
    -0.09
    rosso
    -0.09
    æIJĤ
    -0.09
    MENT
    -0.08
    estion
    -0.08
    PropertyName
    -0.08
    POSITIVE LOGITS
    ä¼ļ计å¸Ī
    0.15
    ä¼ļ计
    0.11
    èĶļ
    0.11
    å®ŀåĬ¡
    0.10
    æī§ä¸ļ
    0.09
    XB
    0.09
    æĸ¹åľĨ
    0.09
    è·»
    0.09
    审计
    0.09
    计éĩı
    0.09
    Activations Density 0.085%

    No Known Activations