© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 10597
    Prev
    Next
    INDEX
    Explanations

    connection point

    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
    éļİ
    -0.08
    踩
    -0.08
    éĤ£éĩĮ
    -0.08
    å¦Ĩ
    -0.08
     thereof
    -0.07
     özellikleri
    -0.07
    åħ¶
    -0.07
    icont
    -0.07
    åŀĤ
    -0.07
    _RST
    -0.07
    POSITIVE LOGITS
    è¿Ļ款
    0.13
    æľ¬ç½ijç«Ļ
    0.12
    äºĨæĪijçļĦ
    0.11
    è¿Ļ款游æĪı
    0.11
    æľ¬ç«Ļ
    0.10
    æľ¬ç½ij
    0.10
    è¿Ļå®¶
    0.09
    _THIS
    0.09
    æľ¬æ¬¡
    0.09
    è¿Ļé¦ĸæŃĮ
    0.09
    Activations Density 0.526%

    No Known Activations