© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10409
    Prev
    Next
    INDEX
    Explanations

    future challenges or events

    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
    quate
    -0.09
     Sheffield
    -0.09
    æģ¯
    -0.08
    ç¾Ĭæ¯Ľ
    -0.08
    .updated
    -0.08
    è¸
    -0.08
    æľĢåIJİä¸Ģ个
    -0.08
     rowNum
    -0.08
    iso
    -0.08
    .hs
    -0.08
    POSITIVE LOGITS
    漫éķ¿
    0.12
    åīįæĸ¹
    0.11
    пеÑĢед
    0.11
    åīįæĻ¯
    0.11
    åīįéĢĶ
    0.11
    漫éķ¿çļĦ
    0.10
    èī°å·¨
    0.10
    ç»Ĥ
    0.10
    è·¯ç¨ĭ
    0.09
    éļ¾åħ³
    0.09
    Activations Density 0.197%

    No Known Activations