© 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. 21224
    Prev
    Next
    INDEX
    Explanations

    department address

    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
    çļĦ巨大
    -0.10
    èģĶç³»æĪij们
    -0.10
    éļıä¹ĭ
    -0.09
    åħ¶æ¬¡
    -0.09
    å°ĸ
    -0.08
    人家
    -0.08
    pañ
    -0.08
    å¦Ĥä»Ĭ
    -0.08
    ivant
    -0.08
    avi
    -0.08
    POSITIVE LOGITS
     unre
    0.09
    éĺ¿æł¹
    0.08
    æĦı大
    0.08
    å¥Ĺ
    0.08
    åĪĨæīĭ
    0.08
    Ess
    0.08
    注æĦıåĬĽ
    0.08
    -native
    0.08
    äºĨä¸Ģ份
    0.08
    ëĦIJ
    0.08
    Activations Density 0.051%

    No Known Activations