© 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. 51716
    Prev
    Next
    INDEX
    Explanations

    artificial neural networks

    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
     neglig
    -0.09
    AR
    -0.09
     AR
    -0.08
    ç¥Ī祷
    -0.08
    磮
    -0.08
    omp
    -0.08
     nonzero
    -0.08
     fid
    -0.08
    idable
    -0.08
    è´¡çĮ®
    -0.08
    POSITIVE LOGITS
    ç¥ŀç»ı
    0.11
    缴éĶĢ
    0.09
     neuron
    0.09
    çļĦåŃ¦ä¹ł
    0.09
    è¯ģåĪ¸æĬķèµĦ
    0.08
    模仿
    0.08
     Cruise
    0.08
    輸
    0.08
    注éĶĢ
    0.08
    bill
    0.08
    Activations Density 0.152%

    No Known Activations