© 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. 8808
    Prev
    Next
    INDEX
    Explanations

    cancer pain and care

    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
    åĤħ
    -0.10
    entic
    -0.10
    æѧ
    -0.09
    çĹ´è¿·
    -0.08
    arem
    -0.08
    å»ºåĽ½
    -0.08
    åģ¥èº«
    -0.08
    .isNull
    -0.08
     kiá»ĩn
    -0.08
    åı¬åĽŀ
    -0.07
    POSITIVE LOGITS
    hed
    0.10
     íĻĪ
    0.10
    æŁı
    0.10
    æĪijçľģ
    0.09
    éĵĤ
    0.09
     Kü
    0.09
    翻身
    0.09
    åºĶåıĬæŶ
    0.09
    èĵī
    0.09
     Humph
    0.09
    Activations Density 0.356%

    No Known Activations