© 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. 21989
    Prev
    Next
    INDEX
    Explanations

    energy efficiency

    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
    åħ¥å¢ĥ
    -0.11
     Truck
    -0.10
     Liqu
    -0.09
    íĥķ
    -0.09
    íĹĪ
    -0.09
    alone
    -0.09
    sons
    -0.09
    è·¨
    -0.08
    æŀ¶åŃIJ
    -0.08
     restarted
    -0.08
    POSITIVE LOGITS
    å¢Ģ
    0.11
    sie
    0.10
    æĬ«
    0.10
    kowski
    0.09
    æĻ®
    0.09
    çĦ¦æĢ¥
    0.09
    æİĢ
    0.09
    离
    0.09
    温æļĸ
    0.09
    åį¯
    0.09
    Activations Density 0.059%

    No Known Activations