© 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. 16918
    Prev
    Next
    INDEX
    Explanations

    even as

    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
    çĮ·
    -0.10
    edar
    -0.09
    æĽ´æľī
    -0.09
    éĵĦ
    -0.08
    é¦ĸåħĪæĺ¯
    -0.08
    æ¯ķç«Łæĺ¯
    -0.08
    åĢ¼å¾Ĺ
    -0.08
    age
    -0.08
    ién
    -0.08
    ä»Ģä¹ĪæŶåĢĻ
    -0.08
    POSITIVE LOGITS
    åİĺ
    0.08
    amburger
    0.08
    ä¿ĿæĮģçĿĢ
    0.08
    鲫
    0.08
    Sexy
    0.08
    ewan
    0.08
    æŀģå¤§åľ°
    0.08
    èµĺ
    0.08
    大桥
    0.08
    èĨĽ
    0.08
    Activations Density 0.006%

    No Known Activations