© 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. 10948
    Prev
    Next
    INDEX
    Explanations

    underlying theoretical concepts

    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
    åĽĽä¸ªæĸ¹éĿ¢
    -0.10
    è¦ģåģļ好
    -0.10
    ä¸ī个æĸ¹éĿ¢
    -0.09
    ä¸ĩåįĥ
    -0.09
    åĴ¯
    -0.09
    ä¸įå¿ħ
    -0.09
    éĿŀ常é«ĺ
    -0.09
    aley
    -0.09
    éĿŀ常åĸľæ¬¢
    -0.09
    ä½ĨæĪij
    -0.09
    POSITIVE LOGITS
     nor
    0.16
    åĵªæĢķ
    0.14
     سÙĪÙī
    0.14
    æľīä»»ä½ķ
    0.14
    羣æŃ£çļĦ
    0.13
    羣æŃ£
    0.13
    åĵªæĢķæĺ¯
    0.13
    åºĶæľīçļĦ
    0.13
     ÑħоÑĤÑĮ
    0.11
    ä¹Łæ²¡æľī
    0.11
    Activations Density 0.165%

    No Known Activations