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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8070
    Prev
    Next
    INDEX
    Explanations

    information about how-to or problem resolution

    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
    æľ¬è½®
    -0.12
    æĸ°çļĦä¸Ģå¹´
    -0.10
    äºī缸
    -0.10
    æŃ£åľ¨
    -0.10
    åįĥå¹´
    -0.10
    ä¸Ģ线
    -0.10
    æŃ£åľ¨è¿Ľè¡Į
    -0.09
    æĭ¿åĩºæĿ¥
    -0.09
    说ä¸įå®ļ
    -0.09
    æŃ£æĸĩ
    -0.09
    POSITIVE LOGITS
    çŃ¹èµĦ
    0.10
    ancel
    0.09
    åħĭæľį
    0.09
    åľºåľ°
    0.08
    æĹ¥å¤ľ
    0.08
    ä¹°äºĨ
    0.08
     sourced
    0.08
    è¾ŀèģĮ
    0.08
    æī©å¤§
    0.08
     Hope
    0.08
    Activations Density 0.232%

    No Known Activations