© 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. 26030
    Prev
    Next
    INDEX
    Explanations

    time and date stamps

    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
    á»ħ
    -0.10
    åijĬ
    -0.08
    \/
    -0.08
     СмоÑĤÑĢ
    -0.08
    åĢĴéľī
    -0.08
    uzzi
    -0.07
    sep
    -0.07
    Ñģк
    -0.07
     Laud
    -0.07
    æĺ¼å¤ľ
    -0.07
    POSITIVE LOGITS
    ä¸įçŁ¥ä¸įè§ī
    0.10
    ä¸ĬäºĨ
    0.09
    大æłij
    0.09
    æ°Ĺ軽ãģ«
    0.09
    aal
    0.09
    äºīåĪĽ
    0.09
    å¹¢
    0.09
    ëĦĺ
    0.08
    æĬ¹
    0.08
    Acts
    0.08
    Activations Density 0.079%

    No Known Activations