© 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. 4452
    Prev
    Next
    INDEX
    Explanations

    political leaders and government officials

    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
     pul
    -0.09
    å·¥ç¨ĭå¸Ī
    -0.09
    æĬ«
    -0.09
    ÙĪØ°
    -0.08
    æµĶ
    -0.08
     ÐļÑĥ
    -0.08
    该éĻ¢
    -0.08
    æĦı大
    -0.08
    -tested
    -0.08
    permission
    -0.08
    POSITIVE LOGITS
    é«»
    0.11
    èİĵ
    0.09
    engo
    0.09
    æ»ĭçĶŁ
    0.09
    ideshow
    0.09
    è¾ĩ
    0.09
    кÑĢа
    0.09
    ADVERTISEMENT
    0.09
    éĤĪ
    0.08
    头éĥ¨
    0.08
    Activations Density 0.030%

    No Known Activations