© 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. 48527
    Prev
    Next
    INDEX
    Explanations

    keep up with

    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
    ä¹ĭå¤ľ
    -0.10
    ëĭ¨
    -0.10
    .hl
    -0.10
    æĦıä¹īä¸ĬçļĦ
    -0.09
    	sys
    -0.09
    æ²»
    -0.09
    ardo
    -0.09
     rigged
    -0.09
    ardown
    -0.09
    ä¸ļ绩
    -0.09
    POSITIVE LOGITS
    è·Łä¸įä¸Ĭ
    0.20
    éĢĤåºĶ
    0.15
     pace
    0.14
    赶ä¸Ĭ
    0.12
    è·ŁçĿĢ
    0.11
    è¿Ľåº¦
    0.11
    è·Łè¿Ľ
    0.10
    åºĶ对
    0.10
    赶
    0.10
    åĮ¹éħį
    0.10
    Activations Density 0.046%

    No Known Activations