© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35152
    Prev
    Next
    INDEX
    Explanations

    one unit

    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
    延误
    -0.11
    æ·Ļ
    -0.10
    ä¸įåĪĨ
    -0.09
    离ä¸įå¼Ģ
    -0.09
    èĵĦ
    -0.09
    THR
    -0.09
    è¶Ĭæĺ¯
    -0.09
    ·»
    -0.09
    ifes
    -0.09
    åĬ¨éĿĻ
    -0.09
    POSITIVE LOGITS
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.09
    æĪĸå¤ļ
    0.09
    ä¸Ģå°ı
    0.08
    ISE
    0.08
    以为
    0.08
    ä¸Ģç»Ħ
    0.08
     صاÙĦØŃ
    0.08
    ise
    0.08
     ÙħÙĨÙĩÙħ
    0.08
    å°ıé¢Ŀ
    0.08
    Activations Density 0.144%

    No Known Activations