© 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. 632
    Prev
    Next
    INDEX
    Explanations

    a [noun]

    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
    imuth
    -0.10
    поÑĤ
    -0.09
    親
    -0.09
    ä¸ĢåĪĩ
    -0.09
    .bootstrap
    -0.09
    GOR
    -0.09
    亲
    -0.08
    辨
    -0.08
    çļĦä¸ĢåĪĩ
    -0.08
    ç«Ł
    -0.08
    POSITIVE LOGITS
    å·§åIJĪ
    0.13
    æĴŀ
    0.10
    ARED
    0.10
     matter
    0.09
    å¤ļä¹Ī
    0.09
    å¹Į
    0.09
     coincidence
    0.08
    åĽ¢ç»ĵ
    0.08
    æĢİä¹ĪåĽŀäºĭ
    0.08
    å½ĵå±Ģ
    0.08
    Activations Density 0.078%

    No Known Activations