© 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. 8482
    Prev
    Next
    INDEX
    Explanations

    coalition and partner organizations

    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
    æĪijåĴĮ
    -0.09
    æ¯ıä¸Ģ
    -0.09
    ä¸İåħ¶ä»ĸ
    -0.09
    派驻
    -0.09
    å®īå®ļ
    -0.08
    _connect
    -0.08
    æį¢
    -0.08
    åĿIJèIJ½äºİ
    -0.08
    飬
    -0.08
    æĥ¹
    -0.08
    POSITIVE LOGITS
    åħ±åIJĮ
    0.17
    èģĶåIJĪ
    0.16
    èģ¯åIJĪ
    0.13
    ç»ĦæĪIJçļĦ
    0.13
    ä¸īæĸ¹
    0.12
    åħ±åIJĮåĬªåĬĽ
    0.11
    ä¸Ģèµ·
    0.11
     together
    0.11
    ä¸Ģèĩ´
    0.11
    èģĶ
    0.11
    Activations Density 0.136%

    No Known Activations