© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47489
    Prev
    Next
    INDEX
    Explanations

    is the most

    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
    Negative Logits
    äºĨåIJ§
    -0.11
    å¬
    -0.10
    äºĨåįĬ天
    -0.10
    楼主
    -0.09
    äºĨåĩºæĿ¥
    -0.09
     Claus
    -0.09
    ä½Ĩ她
    -0.09
    äºĨåIJĹ
    -0.09
    äºĨèµ·æĿ¥
    -0.09
    ä½ĨæĪij们
    -0.08
    POSITIVE LOGITS
    é£Łæ¬²
    0.09
    éĻ¤æѤ
    0.09
    ounce
    0.09
    lessly
    0.09
    UDGE
    0.08
    åĩĭ
    0.08
    ï¼
    0.08
    æĪĸèĢħ说
    0.08
    á»Ŀ
    0.08
    åı¸
    0.08
    Activations Density 3.633%

    No Known Activations