© 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. 10514
    Prev
    Next
    INDEX
    Explanations

    you or yours

    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
    èµĺ
    -0.09
    çŃīåĪ°
    -0.09
    æīĵå¼ĢäºĨ
    -0.08
     ÑħоÑĤÑĮ
    -0.08
    è¿Ļ件äºĭæĥħ
    -0.08
    åĩĽ
    -0.08
    ä¸įæĺ¯å¾Ī
    -0.08
    说çļĦæĺ¯
    -0.08
    è¦ģçľĭ
    -0.08
    åİ¥
    -0.08
    POSITIVE LOGITS
    ä½łä¹Ł
    0.17
     yours
    0.16
     YOU
    0.16
    ãģĤãģªãģŁãģ®
    0.16
    ä½łèĩªå·±
    0.15
    ä½łæĺ¯
    0.15
    æĺ¯ä½ł
    0.14
     YOUR
    0.14
    æĤ¨çļĦ
    0.14
    å¯¹ä½ł
    0.14
    Activations Density 0.132%

    No Known Activations