© 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. 55854
    Prev
    Next
    INDEX
    Explanations

    graphic design and publishing

    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
     Alg
    -0.11
    åľ°ä¸ĭ室
    -0.09
    FirstChild
    -0.09
     Burke
    -0.09
     alg
    -0.09
    ยà¸ģ
    -0.09
    æĪ¿éĹ´
    -0.09
    eyJ
    -0.09
    åľ¨åIJĮä¸Ģ
    -0.09
    çľĭä¸įè§ģ
    -0.09
    POSITIVE LOGITS
    ãĥĩãĤ¶ãĤ¤ãĥ³
    0.10
    åĩºçīĪ
    0.09
    设计æĸ¹æ¡Ī
    0.09
    åį°åĪ·
    0.09
    èĢ·
    0.09
    设计
    0.09
    design
    0.09
    à¹ģà¸ļร
    0.09
    稿
    0.09
    åĪ¶ä½ľ
    0.09
    Activations Density 0.109%

    No Known Activations