© 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. 6514
    Prev
    Next
    INDEX
    Explanations

    success overall

    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
    æŃ£åľ¨
    -0.10
    ToF
    -0.09
    ÙĨاÙĨ
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    åľ¨çº¿åĴ¨è¯¢
    -0.08
     пока
    -0.08
    æĬĹè¡¡
    -0.08
    çłĶ究æĬ¥åijĬ
    -0.08
    leton
    -0.08
    å°ļæľª
    -0.08
    POSITIVE LOGITS
    åľĨ满
    0.12
    èIJ½å¹ķ
    0.11
    æĶ¶
    0.10
    åħħ
    0.10
    åľĨ满å®ĮæĪIJ
    0.10
    éģĹæĨ¾
    0.10
    åIJĦçķĮ
    0.09
    满æĦı
    0.09
    Overall
    0.09
     overall
    0.09
    Activations Density 0.074%

    No Known Activations