© 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. 22129
    Prev
    Next
    INDEX
    Explanations

    questioning existence, digits, tools, code, and summaries

    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
    éĤ£æĺ¯
    -0.11
     (
    -0.09
    ãģĿãĤĮãģĮ
    -0.09
    éĤ£
    -0.08
    å®ĥ
    -0.08
    对åħ¶çľŁå®ŀ
    -0.08
    éĻ¤å¤ĸ
    -0.08
    æŃ¤ä¸¾
    -0.08
    ä½ĨçĶ±äºİ
    -0.08
     -
    -0.08
    POSITIVE LOGITS
    以ä¸Ĭ
    0.12
    楼主
    0.12
    è¿ĺæľīå¾Īå¤ļ
    0.12
    æĢ»ä¹ĭ
    0.12
    æĢ»èĢĮè¨Ģä¹ĭ
    0.11
    è¿Ļä¹Īå¤ļ
    0.11
    è¿ĺæľīä¸ĢäºĽ
    0.11
    åıĬ以ä¸Ĭ
    0.11
    è¿Ļåĩł
    0.11
    以ä¸ĬçļĦ
    0.11
    Activations Density 0.132%

    No Known Activations