© 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. 8209
    Prev
    Next
    INDEX
    Explanations

    discussing issues

    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
    ling
    -0.09
    лин
    -0.09
    伶
    -0.08
    ÑģÑĤа
    -0.08
    æľīä¸ĢäºĽ
    -0.08
    åľ¨æĪij
    -0.08
    è¯Ń
    -0.08
    ä¾ĭè¡Į
    -0.08
    è½»è½»åľ°
    -0.08
    essler
    -0.08
    POSITIVE LOGITS
    åĴĮå®ĮåĸĦ
    0.11
    è£ķ
    0.11
    ski
    0.10
    åķĥ
    0.10
    å²±
    0.09
    PIO
    0.09
    ä»İå°ı
    0.09
    åŃIJéĩĮ
    0.09
    AndUpdate
    0.09
     Greenville
    0.08
    Activations Density 0.023%

    No Known Activations