© 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. 8980
    Prev
    Next
    INDEX
    Explanations

    total beginner

    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
    æį§
    -0.11
    èĭŀ
    -0.10
    å¹Ħ
    -0.10
    å¸Ĥåľºè§Ħ模
    -0.09
    OnError
    -0.09
    æ±ģ
    -0.09
    èѦæĸ¹
    -0.09
    翦
    -0.09
    å¯Ħ
    -0.09
    director
    -0.09
    POSITIVE LOGITS
    å¤įåį°ä»¶
    0.10
    å¤ĸæĿ¥
    0.10
    赢家
    0.09
    好人
    0.09
    atel
    0.09
    主ä¹īèĢħ
    0.09
    çİĭèĢħ
    0.09
     lon
    0.09
    isms
    0.08
    æ½ľåľ¨
    0.08
    Activations Density 0.166%

    No Known Activations