© 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. 63168
    Prev
    Next
    INDEX
    Explanations

    technical questions about files, processes, or issues

    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
    agar
    -0.10
    岸
    -0.10
    åĩĿèģļ
    -0.08
    æīįæĺ¯
    -0.08
    æĺ¯ä¸Ģéĥ¨
    -0.08
    ç§ģãĤĤ
    -0.08
    anos
    -0.08
    é¦į
    -0.08
    è£Ļ
    -0.08
    flo
    -0.08
    POSITIVE LOGITS
     nÃły
    0.22
    è¿ĻäºĽ
    0.20
     ÙĩØ°Ùĩ
    0.20
     this
    0.20
    è¿Ļåĩłä¸ª
    0.19
     these
    0.19
    è¿Ļä¸Ģ
    0.18
     dieser
    0.17
    è¿Ļ个
    0.17
    è¿Ļ两个
    0.17
    Activations Density 0.955%

    No Known Activations