© 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. 36063
    Prev
    Next
    INDEX
    Explanations

    unique

    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
    å±ŀå®ŀ
    -0.10
    æĺİ天
    -0.09
    ç´ł
    -0.09
    posted
    -0.09
    çľ¼éĩĮ
    -0.09
     ÑģобÑģÑĤвенно
    -0.09
    æĦıåĽ¾
    -0.08
     вÑģÑı
    -0.08
    ponge
    -0.08
    ä¸ĢåĪĩ
    -0.08
    POSITIVE LOGITS
    çĭ¬çī¹çļĦ
    0.18
    çĭ¬çī¹
    0.16
    çĭ¬ä¸ĢæĹłäºĮ
    0.15
     unique
    0.14
     Ñĥника
    0.14
    (unique
    0.13
     Unique
    0.13
    çļĦçĭ¬çī¹
    0.13
    çĭ¬åħ·
    0.13
     uniquely
    0.13
    Activations Density 0.094%

    No Known Activations