© 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. 3068
    Prev
    Next
    INDEX
    Explanations

    steps, numbers, or lists

    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
    éĢıè§Ĩ
    -0.10
    izz
    -0.09
    ä¸ĢéŨ
    -0.09
    ä½ĵçİ°åľ¨
    -0.08
    æѤ类
    -0.08
    ç¨İåĬ¡æĢ»å±Ģ
    -0.08
    åºĶ该å¦Ĥä½ķ
    -0.08
    angen
    -0.08
    æĽ´æľī
    -0.08
    误ä¼ļ
    -0.08
    POSITIVE LOGITS
    è¦ģä¹Ī
    0.11
    æŃ¥éª¤
    0.11
     steps
    0.10
    ä»Ķç»Ĩ
    0.10
    å°Ĩèĩªå·±çļĦ
    0.09
    Either
    0.09
    å®īå¿ĥ
    0.09
     either
    0.09
    æĪ´ä¸Ĭ
    0.09
     Steps
    0.09
    Activations Density 0.198%

    No Known Activations