© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7025
    Prev
    Next
    INDEX
    Explanations

    highest to first

    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
    ponge
    -0.09
    主人
    -0.09
    æĴ¸
    -0.09
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.09
    dex
    -0.09
     اÙĦجÙĪ
    -0.08
    _globals
    -0.08
    缴æİ¥
    -0.08
    客æłĪ
    -0.08
    èİ«åIJįåħ¶å¦Ļ
    -0.08
    POSITIVE LOGITS
    è°ģèĥ½
    0.13
    å°½åı¯èĥ½
    0.11
    è¶Ĭ好
    0.10
    èĥ½åľ¨
    0.10
    èĥ½è®©
    0.10
    æľĢ好
    0.10
    æľĢ好çļĦ
    0.10
    ä½łèĥ½
    0.10
     ìĸ¼ë§ĪëĤĺ
    0.09
    éĥ½èĥ½å¤Ł
    0.09
    Activations Density 0.042%

    No Known Activations