© 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. 19057
    Prev
    Next
    INDEX
    Explanations

    running or run

    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
    TRL
    -0.10
    è¿Ļè¾ĪåŃIJ
    -0.10
    严峻
    -0.09
    æīij
    -0.09
    翳
    -0.09
    主任
    -0.09
    iant
    -0.08
    éĴĵ
    -0.08
    pond
    -0.08
    enko
    -0.08
    POSITIVE LOGITS
    ä¸ĢæĹı
    0.09
    赤
    0.09
    ksam
    0.09
    è¶ħ级
    0.08
    åįıä¼ļ
    0.08
    маÑĤ
    0.08
    åģ¥
    0.08
    ä¸į失
    0.08
    åįıä¼ļä¼ļåijĺ
    0.08
     اÙĦÙħØ´
    0.08
    Activations Density 0.025%

    No Known Activations