© 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. 52168
    Prev
    Next
    INDEX
    Explanations

    tree bark

    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
    æļ´
    -0.09
    éĺŁåijĺ们
    -0.08
    æľºéģĩ
    -0.08
    æħĬ
    -0.08
    çĪ¶æ¯į
    -0.08
    æĦŁæĤŁ
    -0.08
    ç§ģèĩª
    -0.08
    åݨæĪ¿
    -0.08
    elay
    -0.08
    0
    -0.08
    POSITIVE LOGITS
    æĸij
    0.12
    çļ®
    0.11
     bark
    0.10
    çĮ¿
    0.10
    æĽĻåħī
    0.10
     Bark
    0.09
    缣
    0.09
     окÑĢÑĥг
    0.09
     cortex
    0.09
    çīĪ
    0.09
    Activations Density 0.030%

    No Known Activations