© 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. 57267
    Prev
    Next
    INDEX
    Explanations

    father's successor or death

    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
    纵深
    -0.09
    åłĥ
    -0.09
    åĿĽ
    -0.09
    æĸ°éĻĪ代谢
    -0.09
     Ancient
    -0.09
    åĬłçĽĸ
    -0.09
    Anc
    -0.09
    è¯ļæĦı
    -0.09
    åĪĨæł¡
    -0.09
    太æŀģ
    -0.09
    POSITIVE LOGITS
    éģĹ
    0.17
    éĢĿä¸ĸ
    0.16
    éģĹçķĻ
    0.16
    æŃ»åIJİ
    0.14
    å°¸ä½ĵ
    0.13
    å°¸
    0.13
    å¢ĵ
    0.12
    éģº
    0.12
    æĹ¶ä»£çļĦ
    0.12
    éģĹ迹
    0.12
    Activations Density 0.127%

    No Known Activations