© 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. 22789
    Prev
    Next
    INDEX
    Explanations

    prevent this/these/such

    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
    åı¦ä¸Ģä½į
    -0.10
    ÑĤÑĢÑĥд
    -0.09
    пи
    -0.08
    æªĢ
    -0.08
    说çļĦæĺ¯
    -0.08
    âľı
    -0.08
    çł´
    -0.08
    nde
    -0.07
    اÙĨÙĬ
    -0.07
    åıĪæĺ¯
    -0.07
    POSITIVE LOGITS
    è¿Ļä¸ĢçĤ¹
    0.33
    è¿ĻäºĽ
    0.32
    è¿Ļç§įæĥħåĨµ
    0.31
    è¿Ļç§į
    0.31
    è¿Ļæł·åģļ
    0.30
    è¿Ļä¹Īåģļ
    0.30
    è¿ĻäºĽéĹ®é¢ĺ
    0.29
     these
    0.29
    è¿Ļæĸ¹éĿ¢
    0.28
    è¿Ļä¸ĢåĪĩ
    0.28
    Activations Density 0.935%

    No Known Activations