© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35934
    Prev
    Next
    INDEX
    Explanations

    how something is done

    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
    è¯Ŀ说
    -0.10
    è¦ģ说
    -0.10
    åĬ³åĬ¡
    -0.09
    åķ·
    -0.09
    è°İè¨Ģ
    -0.09
    æľī人说
    -0.09
    åºĶçĶ¨äºİ
    -0.08
    éĹ®é¢ĺæĺ¯
    -0.08
    æĪ¢
    -0.08
    ä¸Ģè¾ĪåŃIJ
    -0.08
    POSITIVE LOGITS
    -done
    0.10
    è·Ł
    0.10
     done
    0.09
     апп
    0.09
     ЮÑĢ
    0.09
    done
    0.09
    足
    0.09
     ÑħоÑĤÑĮ
    0.09
    Done
    0.09
     بÙĪاسطة
    0.08
    Activations Density 0.100%

    No Known Activations