© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34584
    Prev
    Next
    INDEX
    Explanations

    capillary pores and uptake

    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
    æļĸæ°Ķ
    -0.08
    oyal
    -0.08
    ä»ĺ
    -0.08
    çªł
    -0.08
    OrderBy
    -0.08
    积
    -0.08
    åłª
    -0.08
    çĶŁæ´»ä¹łæĥ¯
    -0.08
    eldorf
    -0.08
    æĹ¥çĶµ
    -0.08
    POSITIVE LOGITS
    æ¸ĹéĢı
    0.14
    æ°´åĪĨ
    0.12
    海绵
    0.12
    æ¸Ĺ
    0.12
     perme
    0.11
    浸
    0.11
    æ£īèĬ±
    0.10
    æ¯ĽåŃĶ
    0.10
    æ¼ıæ°´
    0.10
    æ±Ĺæ°´
    0.09
    Activations Density 0.146%

    No Known Activations