© 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. 36976
    Prev
    Next
    INDEX
    Explanations

    I think that

    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
    ä½ķåĨµ
    -0.13
    æĽ´ä½ķåĨµ
    -0.13
    以èĩ´
    -0.10
    以èĩ³äºİ
    -0.10
    åĨµä¸Ķ
    -0.09
    æĢĨ
    -0.09
    å¤©åĽ½
    -0.09
     finally
    -0.08
    esh
    -0.08
    åĺ´è§Ĵ
    -0.08
    POSITIVE LOGITS
    è¿Ļä¹Īåģļ
    0.11
    åģļçļĦ
    0.10
    çĮľ
    0.09
    ÑĦи
    0.09
    å¹³åĿĩæ¯ı
    0.09
    çĦ¶å¾Į
    0.09
    è¿Ļæł·åģļ
    0.09
    çĦ¶åIJİ
    0.08
     najczÄĻÅĽciej
    0.08
    awi
    0.08
    Activations Density 0.538%

    No Known Activations