© 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. 31537
    Prev
    Next
    INDEX
    Explanations

    attending school, church, or events

    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
    åįķ项
    -0.09
    olf
    -0.09
    ä¼ijåģĩ
    -0.08
    uke
    -0.08
    è¸ı
    -0.08
    å¼Ģå±ķ
    -0.08
    ldr
    -0.08
    à¹Ĥà¸Ĺร
    -0.07
    æļĤåģľ
    -0.07
    è¯ł
    -0.07
    POSITIVE LOGITS
    并éĢļè¿ĩ
    0.12
    alsa
    0.11
    æݨä»ĭä¼ļ
    0.11
    .sessions
    0.10
    åıijå¸ĥä¼ļ
    0.10
    æĢ§å¼º
    0.10
    é¦ĸåħĪæĺ¯
    0.10
    ä¸Ģè¶Ł
    0.09
    ë¡Ŀ
    0.09
    Peripheral
    0.09
    Activations Density 0.038%

    No Known Activations