© 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. 7773
    Prev
    Next
    INDEX
    Explanations

    occurrences and events

    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
    .her
    -0.10
    ä¸įå¾Ĺä¸į说
    -0.09
    acco
    -0.09
    ofi
    -0.09
    çľĭä¸Ģçľĭ
    -0.09
    çľĭå¾Ĺ
    -0.09
    æ¦ĤåĨµ
    -0.08
    人çļĦ
    -0.08
    è¿Ļæĺ¯ä¸Ģ个
    -0.08
    еÐ
    -0.08
    POSITIVE LOGITS
    åıĺæĪIJäºĨ
    0.14
    åıĺå¾Ĺ
    0.14
    åıĺ为
    0.14
     becomes
    0.13
    åıĺæĪIJ
    0.12
    ä¸įåĨįæĺ¯
    0.12
    å°±æĪIJäºĨ
    0.12
    ä¹Łéļıä¹ĭ
    0.12
    åıĺå¾ĹæĽ´åĬł
    0.11
    è®ĬæĪIJ
    0.11
    Activations Density 0.234%

    No Known Activations