© 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. 48593
    Prev
    Next
    INDEX
    Explanations

    cost of operating or manufacturing

    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
    碴
    -0.09
    æ¨¡æł·
    -0.09
    çļĦæ¨¡æł·
    -0.08
    æĦıåĽ¾
    -0.08
    æĹ¢åı¯ä»¥
    -0.08
    çģµéŃĤ
    -0.08
    åįİ润
    -0.08
    ç»ıèIJ¥èĮĥåĽ´
    -0.08
    æīĭæĦŁ
    -0.08
    å·¨åŀĭ
    -0.08
    POSITIVE LOGITS
    çļĦæĪIJæľ¬
    0.14
    æĪIJæľ¬
    0.14
     costs
    0.14
    è´¹çĶ¨
    0.13
    cost
    0.12
     cost
    0.12
     kosten
    0.12
     costo
    0.11
     Costs
    0.11
    Cost
    0.11
    Activations Density 0.202%

    No Known Activations