© 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. 2701
    Prev
    Next
    INDEX
    Explanations

    heating and cooling

    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
    对æĪij
    -0.09
    aced
    -0.09
    讲å¸Ī
    -0.09
    oz
    -0.09
    bred
    -0.08
    oad
    -0.08
    ä¸ĢæĬ¹
    -0.08
    ober
    -0.08
    uze
    -0.08
    mium
    -0.08
    POSITIVE LOGITS
    æķ´ä¸ª
    0.11
    èĶĵ
    0.10
    è¿Ļ座åŁİå¸Ĥ
    0.09
    è¿Ļ个ä¸ĸçķĮ
    0.09
    åĬĽæ±Ĥ
    0.09
    æĪij们çļĦ
    0.09
    æ¯ıä¸Ģ个
    0.09
     entire
    0.09
    æľºä½ĵ
    0.09
    ä»»ä½ķä¸Ģ个
    0.09
    Activations Density 0.448%

    No Known Activations