© 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. 20967
    Prev
    Next
    INDEX
    Explanations

    social media and interactions

    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
    erializer
    -0.09
     exp
    -0.08
    æĻŁ
    -0.08
    룰
    -0.08
    isman
    -0.08
     rivals
    -0.08
    exp
    -0.08
    æĭĨ
    -0.08
    uled
    -0.07
    éĺ
    -0.07
    POSITIVE LOGITS
    åľºåIJĪ
    0.11
    verständlich
    0.10
    æĢ§å¼º
    0.10
    ware
    0.10
    èµ·æĿ¥äºĨ
    0.09
    æĦıè¯Ĩ
    0.09
    athe
    0.09
    æĩ¿
    0.09
    able
    0.09
    çŃ¹
    0.09
    Activations Density 0.020%

    No Known Activations