© 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. 37402
    Prev
    Next
    INDEX
    Explanations

    honors program or curriculum

    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
    éĺ²åį«
    -0.09
    cake
    -0.09
    fa
    -0.08
    bia
    -0.08
    è¿ĩåī©
    -0.08
     slides
    -0.08
     diag
    -0.08
    éķ¿æķĪæľºåĪ¶
    -0.08
    ila
    -0.08
    ifi
    -0.08
    POSITIVE LOGITS
    å¿ĥåĬ¨
    0.10
    æľºåŀĭ
    0.09
     ngũ
    0.09
    è¡ĮåĪĹ
    0.09
    ::__
    0.09
     Burg
    0.08
    LOOP
    0.08
    à¹Ĥย
    0.08
    .decorate
    0.08
    iol
    0.08
    Activations Density 0.007%

    No Known Activations