© 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. 36775
    Prev
    Next
    INDEX
    Explanations

    time in minutes

    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
     Magnum
    -0.10
    çŁŃæľŁåĨħ
    -0.09
    .dtd
    -0.09
    éĢIJå¹´
    -0.09
     Manual
    -0.09
     Miche
    -0.08
    åĪ°æŶåĢĻ
    -0.08
    æĸĭ
    -0.08
     manual
    -0.08
    manual
    -0.08
    POSITIVE LOGITS
    åįģåĪĨéĴŁ
    0.10
    åĩłåĪĨéĴŁ
    0.10
    çĸij
    0.10
    å±ıå¹ķä¸Ĭ
    0.09
    çļĦæ¯ĶèµĽ
    0.09
    æŶéĹ´ä¸º
    0.09
    æĹ¶æ®µ
    0.09
    æ¯ĶèµĽä¸Ń
    0.09
    æŃ£åĢ¼
    0.09
    æĤ¬å¿µ
    0.09
    Activations Density 0.017%

    No Known Activations