© 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. 29946
    Prev
    Next
    INDEX
    Explanations

    frequency and quantity

    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
    æľĢåħĪ
    -0.09
    æ¸Į
    -0.08
    åIJµ
    -0.08
    çļĦçģµéŃĤ
    -0.08
    æĨĤ
    -0.07
    ä¸ĢéĶ®
    -0.07
    èĩ³äºİ
    -0.07
    ãģłãģijãģ§
    -0.07
    æľĢæĹ©
    -0.07
    oret
    -0.07
    POSITIVE LOGITS
    æĽ´å¤ļçļĦæĺ¯
    0.13
    çļĦæĥħåĨµä¸ĭ
    0.10
    æ³¢
    0.10
    æĭ±
    0.10
    ä¸įçĦ¶
    0.10
    æĥħåĨµä¸ĭ
    0.10
    à¹Ĥà¸Ľà¸£à¹ģ
    0.10
    ä¸ļ
    0.09
    -Aug
    0.09
    à¹ģà¸ŀ
    0.09
    Activations Density 0.055%

    No Known Activations