© 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. 31474
    Prev
    Next
    INDEX
    Explanations

    normally, usually

    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
    å¤ļå¹´åīį
    -0.10
    æľīå¿ħè¦ģ
    -0.10
    çľĭäºĨä¸Ģ
    -0.10
    å¤ļå¹´
    -0.10
    æijĩäºĨæijĩ头
    -0.10
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.10
    çľĭäºĨçľĭ
    -0.09
    åĽŀåĪ°äºĨ
    -0.09
    ä»įæĺ¯
    -0.09
    çħ§æł·
    -0.09
    POSITIVE LOGITS
     Normally
    0.12
     normally
    0.12
    æѤ类
    0.10
    normally
    0.10
    è¿Ļ个æŶåĢĻ
    0.10
    å¦ĤæѤ
    0.10
     xuyên
    0.09
    åģļæ³ķ
    0.08
    Normally
    0.08
    æĥ¯ä¾ĭ
    0.08
    Activations Density 0.064%

    No Known Activations