© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 23172
    Prev
    Next
    INDEX
    Explanations

    they, them, these, each

    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
    å¤ļå±Ĥ次
    -0.10
    大å¤ļæĺ¯
    -0.09
    ä¸īæĸ¹
    -0.09
    å¤ļç§į
    -0.09
    å±Ĥå±Ĥ
    -0.09
    åĽ´è§Ĥ
    -0.09
    大å¤ļ
    -0.09
    éĢIJä¸Ģ
    -0.09
     çeÅŁitli
    -0.09
    åĽĽæĸ¹
    -0.09
    POSITIVE LOGITS
    åıĮåıĮ
    0.26
    ä¿©
    0.26
    è¿Ļ两个
    0.25
    äºĮ人
    0.24
    两ä½į
    0.23
    两个人
    0.22
    åIJĦèĩª
    0.22
    åIJĦèĩªçļĦ
    0.22
    两人
    0.21
    两个
    0.21
    Activations Density 0.445%

    No Known Activations