© 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. 3319
    Prev
    Next
    INDEX
    Explanations

    ACC conference voted

    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
    为åĩĨ
    -0.10
    pio
    -0.09
    éĶĢ
    -0.09
    åľ¨æĹ¥æľ¬
    -0.09
    åľ¨å¹¿å·ŀ
    -0.08
    McC
    -0.08
    gar
    -0.08
    äºĮåįģåĽĽ
    -0.08
    åľ¨æĪijçļĦ
    -0.08
    饼
    -0.08
    POSITIVE LOGITS
    æ±Łæ¹ĸ
    0.11
    åIJķ
    0.09
    æ½ŀ
    0.09
    ington
    0.08
     Koch
    0.08
    强大
    0.08
    rema
    0.08
    eness
    0.08
    强
    0.08
    eca
    0.08
    Activations Density 0.115%

    No Known Activations