© 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. 61788
    Prev
    Next
    INDEX
    Explanations

    social media platforms

    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
    åĨĻåŃĹ
    -0.11
    ä¿¡æģ¯å®īåħ¨
    -0.10
    æĿ³
    -0.09
    èݽ
    -0.09
    åĨµ
    -0.09
    æĦ§
    -0.09
    æ¢Ĩ
    -0.09
    iani
    -0.09
    èģĮä¸ļçĶŁæ¶¯
    -0.09
    å¾µ
    -0.08
    POSITIVE LOGITS
     Facebook
    0.16
    .facebook
    0.14
     Instagram
    0.13
    å¾®åįļ
    0.13
    Facebook
    0.13
     twitter
    0.13
     facebook
    0.13
    .twitter
    0.12
     Twitter
    0.12
    微信
    0.12
    Activations Density 0.118%

    No Known Activations