© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22032
    Prev
    Next
    INDEX
    Explanations

    expressing desire or conditional statements

    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
    åģ¶
    -0.09
    å¼¥
    -0.09
    è¿Ļ个åIJįåŃĹ
    -0.09
    è§ģè¿ĩ
    -0.09
     Burton
    -0.08
    èĢĮéĿŀ
    -0.08
    ä¸ĢæĬ¹
    -0.08
    burger
    -0.08
    æ¯ıä¸Ģ个
    -0.08
    ä¸į代表
    -0.08
    POSITIVE LOGITS
    çļĦæĺ¯
    0.10
    èģļçĦ¦
    0.10
    éĽĨä¸Ńåľ¨
    0.10
    é¦ĸ
    0.10
    çŀĦåĩĨ
    0.09
    éľĩæĥĬ
    0.09
    主è¦ģæĺ¯
    0.09
    æľĢ常è§ģçļĦ
    0.09
    éĺ®
    0.09
    说çļĦæĺ¯
    0.09
    Activations Density 0.478%

    No Known Activations