© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33014
    Prev
    Next
    INDEX
    Explanations

    cancer

    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
    èĸ¤
    -0.10
    ä¸Ŀ
    -0.09
    纵
    -0.09
    æĢİä¹Īçľĭ
    -0.08
    ä¸ĢæĬĬ
    -0.08
    家åħ¬åı¸
    -0.08
    çģ«çĥŃ
    -0.08
     Ideal
    -0.08
    ough
    -0.08
    縱
    -0.08
    POSITIVE LOGITS
    é©Ń
    0.11
    秧
    0.10
     Shank
    0.10
     اÙĦÙĪÙĤ
    0.10
    æķĽ
    0.10
    æĮĤ
    0.09
    éĻį临
    0.09
    åºľ
    0.09
    å°ĨæĿ¥
    0.09
    è¾ĩ
    0.09
    Activations Density 0.302%

    No Known Activations