© 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. 37859
    Prev
    Next
    INDEX
    Explanations

    scoring and achievements

    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
     masses
    -0.09
    å¾Ĺå¾Ī好
    -0.09
    ä¸įçŁ¥
    -0.09
    SCII
    -0.09
    让åѦçĶŁ
    -0.09
    iani
    -0.08
    jspx
    -0.08
    ëī´ìĬ¤
    -0.08
    SCRI
    -0.08
    ixo
    -0.08
    POSITIVE LOGITS
    çŃīå¤ļ项
    0.10
     sheer
    0.10
    第ä¸ĢåIJį
    0.09
    ç¹ģ
    0.09
    çĪ±ç¾İ
    0.09
    æĻº
    0.09
    åįķ项
    0.08
    åIJĥçļĦ
    0.08
    ailing
    0.08
     per
    0.08
    Activations Density 0.036%

    No Known Activations