© 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. 52600
    Prev
    Next
    INDEX
    Explanations

    Ottoman, Song, Tang dynasty

    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
    ä¸İæŶ
    -0.10
    åħ³
    -0.08
    ç¢Ĺ
    -0.08
    æĸ°åįİ社
    -0.07
    ä¸ĵèģĮ
    -0.07
    å¶
    -0.07
    éĥ¢
    -0.07
    .staff
    -0.07
    mos
    -0.07
    ä¸įèī¯
    -0.07
    POSITIVE LOGITS
    æĹ¶æľŁ
    0.12
    æĻļæľŁ
    0.12
    æĹ¶æľŁçļĦ
    0.11
    å¹´éĹ´
    0.11
    æĻĤæľŁ
    0.11
    åĢ¦
    0.11
    åIJİæľŁ
    0.11
    çİĭæľĿ
    0.10
    ä¸Ģç¬Ķ
    0.10
    ä¸įæĪIJ
    0.10
    Activations Density 0.033%

    No Known Activations