© 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. 8614
    Prev
    Next
    INDEX
    Explanations

    wave concepts

    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
    æĹłäºº
    -0.10
    åĵ¥ä¼¦
    -0.10
    çĭIJ
    -0.10
    çĶ³è¯ī
    -0.10
    æī§æķĻ
    -0.10
    亵
    -0.10
    æĻĭ
    -0.09
    åĨ³è®®
    -0.09
    âĮIJ
    -0.09
    åħ¥åĽ´
    -0.09
    POSITIVE LOGITS
    浪
    0.16
     wave
    0.14
    æ³¢
    0.13
     waves
    0.13
     волн
    0.11
    wave
    0.11
    _wave
    0.10
    -wave
    0.10
     sóng
    0.10
     Waves
    0.09
    Activations Density 0.051%

    No Known Activations