© 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. 40210
    Prev
    Next
    INDEX
    Explanations

    objects and transactions

    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
    åIJĮæĥħ
    -0.10
    ä»»ä½ķå½¢å¼ı
    -0.09
    åIJĮç±»
    -0.08
    大å¤ļ
    -0.08
    çºłç¼ł
    -0.08
     Dual
    -0.08
    æ·ļ
    -0.08
    涵çĽĸ
    -0.08
    js
    -0.08
    åįĥæĸ¹çĻ¾è®¡
    -0.08
    POSITIVE LOGITS
    å®ŀæŶ
    0.12
    å¿ĺ
    0.09
    ç¾Ĭ
    0.09
    çī¹å®ļ
    0.09
    åĨī
    0.08
    æ°ij主åħļ
    0.08
    åŃº
    0.08
    çį»
    0.08
    _rl
    0.08
     Ellison
    0.08
    Activations Density 0.299%

    No Known Activations