© 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. 38526
    Prev
    Next
    INDEX
    Explanations

    black finish or face makeup

    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
    ç¼Ŀ
    -0.10
    ä½İä¼°
    -0.10
    odash
    -0.10
    å°ıå¿ĥ
    -0.10
    å¹³å®ī
    -0.10
    温åĴĮ
    -0.09
    å½±ä¸ļ
    -0.09
    ç²¾ç¥ŀæĸĩæĺİ
    -0.09
    ç»ıå¼Ģ
    -0.09
    æĿ¼
    -0.09
    POSITIVE LOGITS
     paint
    0.11
    èĤ¤èī²
    0.09
    æ½į
    0.09
    æ¶ĤæĬ¹
    0.09
    bij
    0.08
    èµŃ
    0.08
    éĶĪ
    0.08
    åľºéĿ¢
    0.08
    èµĭ
    0.08
    ools
    0.08
    Activations Density 0.075%

    No Known Activations