© 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. 38190
    Prev
    Next
    INDEX
    Explanations

    Maori or Tahitian names

    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
     Mog
    -0.09
    Malloc
    -0.09
     Sharma
    -0.08
    ÑĤи
    -0.08
    zym
    -0.08
    æĿ§
    -0.08
     tense
    -0.08
    躺çĿĢ
    -0.08
    èĴĻ
    -0.08
    assa
    -0.08
    POSITIVE LOGITS
    è¾Ī
    0.11
    æ©ĩ
    0.10
    以人为
    0.10
    æĸ°ä¸ŃåĽ½
    0.09
    çķĽ
    0.09
    æĦıæĢĿæĺ¯
    0.09
    åİĨæĿ¥
    0.09
    èĪĶ
    0.09
    说åĪ°è¿ĻéĩĮ
    0.09
    å½¼æѤ
    0.09
    Activations Density 0.033%

    No Known Activations