© 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. 24236
    Prev
    Next
    INDEX
    Explanations

    reported speech verbs

    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
    éĺĹ
    -0.09
    éŃĦ
    -0.09
    èį£å¹¸
    -0.08
    åŀļ
    -0.08
    nier
    -0.08
    .nio
    -0.08
     Coch
    -0.08
    èĤ¾
    -0.08
    å½ĵä¹ĭ
    -0.08
    æľ¨èĢ³
    -0.08
    POSITIVE LOGITS
    ä¸Ģåı¥
    0.10
    agli
    0.10
    ä¸Ģ声
    0.10
    маг
    0.09
    个æĢ§åĮĸ
    0.09
    è°İ
    0.09
    icle
    0.09
    ãģ°ãģĭãĤĬ
    0.09
    .accuracy
    0.09
    _oc
    0.09
    Activations Density 0.032%

    No Known Activations