© 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. 683
    Prev
    Next
    INDEX
    Explanations

    academic fields and studies

    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
    Pow
    -0.08
     Scientific
    -0.07
    ourced
    -0.07
    è§ī
    -0.07
    BIND
    -0.07
    ä¸Ģä¸ĭåŃIJ
    -0.07
     haul
    -0.07
    åŃļ
    -0.07
    validator
    -0.07
    ticker
    -0.07
    POSITIVE LOGITS
    对çŃĸ
    0.13
    çłĶ究
    0.12
     topics
    0.10
    Topics
    0.10
    _topics
    0.10
    祧
    0.10
    ä¸İæŶ
    0.09
    вл
    0.09
    çļĦçłĶ究
    0.09
     studies
    0.09
    Activations Density 0.345%

    No Known Activations