© 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. 60829
    Prev
    Next
    INDEX
    Explanations

    plus/minus signs and intervals

    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
    ikon
    -0.09
    acle
    -0.09
    å§ĭäºİ
    -0.09
     blas
    -0.08
    blo
    -0.08
    anon
    -0.08
    å©ļ
    -0.08
    æ¡Ī
    -0.08
    _estimator
    -0.08
    ullan
    -0.08
    POSITIVE LOGITS
    ä¸Ĭä¸ĭ
    0.14
     ±
    0.12
    ±
    0.11
     +/-
    0.10
    å¾Īå°ı
    0.10
    è¯Ī
    0.10
    åīįåIJİ
    0.10
    å°ijä¸įäºĨ
    0.09
    å¿į
    0.09
     +-
    0.09
    Activations Density 0.015%

    No Known Activations