© 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. 34688
    Prev
    Next
    INDEX
    Explanations

    meant to or talking about

    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
    ichten
    -0.09
    ç²īæľ«
    -0.08
    åĽ´
    -0.08
    ä¸Ģä¸Ģ
    -0.08
    æĦİ
    -0.08
    åħ»æĪIJ
    -0.08
    blr
    -0.08
    åħ»
    -0.08
     fans
    -0.07
    è£Ĥ
    -0.07
    POSITIVE LOGITS
    ä»Ģä¹ĪæĦıæĢĿ
    0.15
    æĦıæĢĿæĺ¯
    0.14
    çļĦæĦıæĢĿ
    0.14
     meant
    0.13
    æĮĩçļĦæĺ¯
    0.12
    åĪ°åºķæĺ¯
    0.12
    è¿Ļåı¥è¯Ŀ
    0.12
    çķ¶æĻĤ
    0.11
    å½ĵæŶ
    0.10
    æĺ¯æĮĩ
    0.10
    Activations Density 0.078%

    No Known Activations