© 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. 53000
    Prev
    Next
    INDEX
    Explanations

    health harming design ownership

    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
    主å¸Ń
    -0.09
    à¹Ģà¸ļ
    -0.09
    çĸĥ
    -0.08
    nil
    -0.08
    é©·
    -0.08
    æĬĵ
    -0.08
    å©Ģ
    -0.08
    åĩłä¹İæīĢæľī
    -0.08
    -scalable
    -0.08
    çłĶ究æĬ¥åijĬ
    -0.08
    POSITIVE LOGITS
     Roth
    0.09
    æĮģæľīçļĦ
    0.09
    (SIG
    0.09
    ä¸įä»ħå¦ĤæѤ
    0.08
    ÙĪا
    0.08
    alchemy
    0.08
    åľ¨æĪijçľĭæĿ¥
    0.08
    æݨèįIJéĺħ读
    0.08
    å¿Ĺ强
    0.08
    itecture
    0.08
    Activations Density 0.223%

    No Known Activations