© 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. 4900
    Prev
    Next
    INDEX
    Explanations

    sugar

    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
    çĶŁäº§æĢ»åĢ¼
    -0.10
     дело
    -0.09
    è¿ĩå¾Ĺ
    -0.09
    olic
    -0.09
    赤
    -0.09
    æıĴ
    -0.09
    sole
    -0.09
    淹没
    -0.09
    vault
    -0.09
    ives
    -0.09
    POSITIVE LOGITS
    è¯ļæĦı
    0.09
    å³Ļ
    0.08
    éĽī
    0.08
    æĸĩç«łæĿ¥æºIJ
    0.08
    lek
    0.08
    SharedPtr
    0.08
    (dw
    0.08
     Jennings
    0.08
    developers
    0.08
    对æĸ¹
    0.08
    Activations Density 0.003%

    No Known Activations