© 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. 1842
    Prev
    Next
    INDEX
    Explanations

    one or both

    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
    asher
    -0.10
    çħ§æł·
    -0.09
    ä¸ĢèĪ¬çļĦ
    -0.08
    ìŀ¥ìĿĦ
    -0.08
    ãĤ¿ãĥ³
    -0.08
    没æľīä»Ģä¹Ī
    -0.08
    æ®Ĭ
    -0.08
    éľŀ
    -0.08
    æİĴåIJį第
    -0.08
    ØŃÙĥ
    -0.08
    POSITIVE LOGITS
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.12
    æĪĸå¤ļ
    0.11
    ä¸Ģæĸ¹
    0.11
    ëĿ¼ëıĦ
    0.11
    æĭİ
    0.10
    æľĪä¸Ń
    0.10
    either
    0.10
     either
    0.10
     SAY
    0.09
    æī§
    0.09
    Activations Density 0.102%

    No Known Activations