© 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. 51282
    Prev
    Next
    INDEX
    Explanations

    critical biological and metabolic functions

    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
    theses
    -0.09
    æĸ¯
    -0.09
    æ·±æ¸Ĭ
    -0.09
    åŁ´
    -0.09
    åIJĮä¸ļ
    -0.09
    ipi
    -0.09
    æĢ§ä»·
    -0.09
    åłł
    -0.09
     Gord
    -0.09
    orca
    -0.09
    POSITIVE LOGITS
    主ä¸ļ
    0.15
    æ´»åĬ¨ä¸Ń
    0.11
    æ´»åĬ¨
    0.11
    çĶŁäº§ç»ıèIJ¥
    0.11
    ç»ıèIJ¥æ´»åĬ¨
    0.10
     деÑıÑĤелÑĮноÑģÑĤи
    0.10
     activity
    0.10
    主èIJ¥ä¸ļåĬ¡
    0.10
    çŃīæ´»åĬ¨
    0.10
    æ´»åĭķ
    0.10
    Activations Density 0.046%

    No Known Activations