© 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. 38436
    Prev
    Next
    INDEX
    Explanations

    names and family roles

    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
    æĹłè§Ĩ
    -0.12
    她们
    -0.12
    ä½łä»¬
    -0.11
    å®ĥ们
    -0.11
    ä¹³
    -0.10
    ä¸į顾
    -0.10
    ä»ĸ们çļĦ
    -0.09
    å°ıç¼ĸ
    -0.09
    æĪijåĴĮ
    -0.09
    è¿ĺæĺ¯è¦ģ
    -0.09
    POSITIVE LOGITS
    åijĬè¯īä»ĸ
    0.11
    ç»Ļä»ĸ
    0.11
    æħķ
    0.10
    帮ä»ĸ
    0.10
    æĺ¯ä»ĸ
    0.10
    为åħ¶
    0.09
    è®ĵä»ĸ
    0.09
    沫
    0.09
    iday
    0.08
    æ¸Ĭ
    0.08
    Activations Density 0.204%

    No Known Activations