© 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. 10426
    Prev
    Next
    INDEX
    Explanations

    names and possessives

    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
     Whats
    -0.09
    åįĩ级æĶ¹éĢł
    -0.09
    亿ä¸ĩ
    -0.09
    åħijçİ°
    -0.08
     [...]↵↵
    -0.08
     Millennium
    -0.08
    ä¹Łéļıä¹ĭ
    -0.08
    wyn
    -0.08
    éĽĨåĽ¢èĤ¡ä»½
    -0.08
    çķ°ãģªãĤĭ
    -0.08
    POSITIVE LOGITS
    éĤ£è¾¹
    0.11
    éĤ£æł·çļĦ
    0.11
    为æĪij们
    0.11
    ç»ĻæĪij们
    0.10
    åľ¨è¿Ļæĸ¹éĿ¢
    0.10
    çļĦéĤ£ä¸ª
    0.10
    ฯ
    0.10
    éĤ£ä¹Ī
    0.10
    éĤ£ç§į
    0.09
    éĤ£ä¹Īç®Ģåįķ
    0.09
    Activations Density 0.227%

    No Known Activations