© 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. 8181
    Prev
    Next
    INDEX
    Explanations

    on the occasion

    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
    ech
    -0.10
    åŁ¹
    -0.09
    abis
    -0.08
     اÙĦØŃدÙĬØ«
    -0.08
    elts
    -0.08
    _CRC
    -0.08
    ç´¯
    -0.08
    æģ¶æĦı
    -0.08
    飦
    -0.08
    åIJIJ
    -0.07
    POSITIVE LOGITS
    åľºåIJĪ
    0.24
     occasion
    0.21
     occasions
    0.20
    occasion
    0.18
     occas
    0.15
     ocas
    0.13
    åºĨåħ¸
    0.13
    à¹Ĥà¸Ńà¸ģาส
    0.13
    åł´åIJĪ
    0.12
     اÙĦÙħÙĨاسب
    0.11
    Activations Density 0.076%

    No Known Activations