© 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. 20776
    Prev
    Next
    INDEX
    Explanations

    by which I mean

    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
    iad
    -0.10
    丢äºĨ
    -0.08
     Accord
    -0.08
    麻
    -0.08
    æĮº
    -0.08
    ilder
    -0.08
    åį´è¢«
    -0.08
    çŃĶåºĶ
    -0.08
    urma
    -0.08
    亢
    -0.08
    POSITIVE LOGITS
    æĮĩçļĦæĺ¯
    0.28
    æĦıæĢĿæĺ¯
    0.26
    æĺ¯æĮĩ
    0.26
    çļĦæĦıæĢĿ
    0.24
    æĦıæĢĿ
    0.21
    ä¹Łå°±æĺ¯è¯´
    0.20
    æĮĩ
    0.20
    æĦıåij³çĿĢ
    0.19
    ä»Ģä¹ĪæĦıæĢĿ
    0.19
    è¿ĻæĦıåij³çĿĢ
    0.18
    Activations Density 0.184%

    No Known Activations