© 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. 36353
    Prev
    Next
    INDEX
    Explanations

    follower count and fans

    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
    ç¯Ŀ
    -0.10
    æĹłä¸į
    -0.09
    üp
    -0.08
    ãģĦãģıãģ¤ãģĭ
    -0.08
    éĻª
    -0.08
    æĢ¯
    -0.08
    çİĸ
    -0.08
    etty
    -0.08
    æĹģ
    -0.08
    åŃ¦å®¶
    -0.08
    POSITIVE LOGITS
    ç²īä¸Ŀ
    0.20
    åıĹä¼Ĺ
    0.18
    è§Ĥä¼Ĺ
    0.16
     fans
    0.16
    Fans
    0.16
    fans
    0.15
     followers
    0.15
     audience
    0.15
    åIJ¬ä¼Ĺ
    0.14
    followers
    0.14
    Activations Density 0.109%

    No Known Activations