© 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. 37482
    Prev
    Next
    INDEX
    Explanations

    challenging traditional ideas or norms

    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
    æĩĭ
    -0.10
    缯
    -0.09
    çĶ¥
    -0.09
    æīĢéľĢçļĦ
    -0.09
    ä¸Ģåī¯
    -0.08
     ank
    -0.08
    çľ·
    -0.08
     Uploaded
    -0.08
     Bedrooms
    -0.08
    è°ĥæŁ¥
    -0.08
    POSITIVE LOGITS
    æĮijæĪĺ
    0.11
    åıijå±ķæł¼å±Ģ
    0.10
    çĶ³è¯ī
    0.09
    åīįæīĢæľªæľī
    0.09
    åıijå±ķ模å¼ı
    0.09
    æĪIJéķ¿ä¸º
    0.09
    iban
    0.09
    å®ĵ
    0.09
     Challenge
    0.09
    æijĩäºĨ
    0.09
    Activations Density 0.018%

    No Known Activations