© 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. 52189
    Prev
    Next
    INDEX
    Explanations

    when something happens

    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
     Evel
    -0.10
    å³Ļ
    -0.09
     Pike
    -0.09
    лиÑĤ
    -0.09
    éªł
    -0.08
     коÑĤоÑĢÑĭÑħ
    -0.08
    妥
    -0.08
    åŀĦ
    -0.08
    çļĦä»»åĬ¡
    -0.08
    çĶļ
    -0.08
    POSITIVE LOGITS
    æĦıè¯ĨåĪ°
    0.09
    è¶Ĭæĺ¯
    0.09
    once
    0.09
    xBE
    0.08
    ä¸ĩä¸Ģ
    0.08
    èĤ¼
    0.08
    soever
    0.08
    ffield
    0.08
    èĦ±
    0.08
    WARE
    0.08
    Activations Density 0.075%

    No Known Activations