© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26591
    Prev
    Next
    INDEX
    Explanations

    or even

    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
    Not in Any Lists

    No Comments

    Negative Logits
    èİĬ
    -0.10
    æĹ¥æ¸IJ
    -0.09
    .echo
    -0.09
    åºĦ
    -0.09
    -Mart
    -0.08
    åĨįä¹Łä¸į
    -0.08
    omp
    -0.08
    ECH
    -0.08
    åıĪæľī
    -0.08
    åıįæŃ£
    -0.08
    POSITIVE LOGITS
     worse
    0.10
    apur
    0.09
     vice
    0.09
    åľ¨åIJĮä¸Ģ
    0.08
    ä¹Łå¥½
    0.08
    ä¸įå®Į
    0.08
    acre
    0.08
    éģ¥
    0.08
    åıįä¹ĭ
    0.08
    nen
    0.08
    Activations Density 0.011%

    No Known Activations