© 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. 40057
    Prev
    Next
    INDEX
    Explanations

    partners or collaboration

    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
    æ´¸
    -0.09
    åĴ½
    -0.09
    æĽĿåħī
    -0.09
    åĶı
    -0.08
    åIJ¸å¼ķäºĨ
    -0.08
     NAND
    -0.08
     Mund
    -0.08
     master
    -0.07
    awi
    -0.07
    lick
    -0.07
    POSITIVE LOGITS
    ä¸īæĸ¹
    0.13
    积æŀģéħįåIJĪ
    0.13
    对è¯Ŀ
    0.12
    磨
    0.11
    åħ±èµ¢
    0.11
    åħ±åIJĮ
    0.11
    ä¸Ģéģĵ
    0.10
    âĶı
    0.10
    éĻį
    0.10
     diálogo
    0.10
    Activations Density 0.075%

    No Known Activations