© 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. 38832
    Prev
    Next
    INDEX
    Explanations

    email addresses and domains

    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
    容纳
    -0.09
    imension
    -0.09
    æ·¡åĮĸ
    -0.09
    è¿Ļä¸Ģ天
    -0.09
    éħ¹
    -0.09
    åĬŁ
    -0.09
    é¹Ĭ
    -0.09
    ymbol
    -0.08
    å¸ĤæĶ¿
    -0.08
    chaft
    -0.08
    POSITIVE LOGITS
    .enc
    0.09
    ä¼ģä¸ļæıIJä¾Ľ
    0.09
    à°Ĺ
    0.09
    ä¹ĭéģĵ
    0.09
    ä»ħä»ħæĺ¯
    0.08
    æĬĬèĩªå·±
    0.08
    å»ĭ
    0.08
    nel
    0.08
    ateur
    0.08
    .com
    0.08
    Activations Density 0.011%

    No Known Activations