© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8876
    Prev
    Next
    INDEX
    Explanations

    the fact that

    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
    éĤ£ç§į
    -0.13
    é¹Ħ
    -0.10
    çļĦæł¹æľ¬
    -0.10
    çļĦéĤ£ç§į
    -0.09
    è¡®
    -0.09
    çļĦå°±æĺ¯
    -0.09
    éĽĨè£ħ
    -0.09
    çļĦæľºä¼ļ
    -0.09
    梦æĥ³
    -0.09
    å°Ĩæĺ¯
    -0.09
    POSITIVE LOGITS
    大å¤ļæķ°
    0.09
    èĢ³è¾¹
    0.08
    ipse
    0.08
    æĹ©æĻļ
    0.08
    å¤ļæķ°
    0.08
    ãĤ¢ãĥ¡ãĥª
    0.08
    packing
    0.08
    ITUDE
    0.08
    æĻ®éģį
    0.08
    è§Ĩ线
    0.08
    Activations Density 0.025%

    No Known Activations