© 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. 20564
    Prev
    Next
    INDEX
    Explanations

    designers, photography, LLCs, and companies

    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
    éļ¾
    -0.09
    dorf
    -0.09
    é¨
    -0.09
    å¾Īéļ¾
    -0.08
    çĸ¼
    -0.08
    éĿ¢åīį
    -0.08
    éĽ£
    -0.08
    碧æ¡ĤåĽŃ
    -0.08
    ä¸įéĢĤåIJĪ
    -0.08
    Ñĭм
    -0.08
    POSITIVE LOGITS
    ä½ľåĿĬ
    0.11
    å·¥ä½ľå®¤
    0.11
    ç½ijç«Ļ
    0.11
    èĩªåªĴä½ĵ
    0.10
    æĪIJç«ĭ以æĿ¥
    0.10
    erland
    0.10
    afil
    0.10
    ç½ijåºĹ
    0.10
    æݨ广
    0.09
    åħ¼èģĮ
    0.09
    Activations Density 0.165%

    No Known Activations