© 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. 21765
    Prev
    Next
    INDEX
    Explanations

    what can you expect?

    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
    åIJ¦åĪĻ
    -0.09
    ovy
    -0.09
    è¿Ļæīįæĺ¯
    -0.09
    ullet
    -0.09
    è¿ĻçĤ¹
    -0.09
     somehow
    -0.09
    æ¢ĥ
    -0.08
    è¿Ļä¹Łæĺ¯
    -0.08
    ä½Ĩæĺ¯æĪij
    -0.08
    ä¸Ŀ毫
    -0.08
    POSITIVE LOGITS
     exactly
    0.13
    æģ°å¥½
    0.10
    ä»Ģä¹Īåij¢
    0.10
    å½ĵçĦ¶æĺ¯
    0.10
    çĮ·
    0.09
    èĩªçĦ¶æĺ¯
    0.09
    ç«ŁçĦ¶
    0.09
    ä½ķå¤Ħ
    0.09
    éĢĤåIJĪèĩªå·±
    0.09
    æŃ£å¥½
    0.09
    Activations Density 0.097%

    No Known Activations