© 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. 31213
    Prev
    Next
    INDEX
    Explanations

    trusted subordinates, leading cadre, legal team, close associate, great-granddaughter, close friendship, faithful servant, backing band

    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
    ÙĨÙĤ
    -0.09
    注æĺİæĿ¥æºIJ
    -0.08
    æĬķ身
    -0.08
    ä¼ļåIJĮ
    -0.08
    icina
    -0.08
     Superior
    -0.08
    WARE
    -0.08
    ongan
    -0.08
    åľ¨å½ĵåľ°
    -0.08
    ä¸Ģ座
    -0.08
    POSITIVE LOGITS
    éĻª
    0.15
    ä¼´éļı
    0.14
    éĻªä¼´
    0.13
    è¾ħåĬ©
    0.12
    éĻªåIJĮ
    0.12
    ä»ħ次äºİ
    0.12
    ä¸įåı¯æĪĸ缺
    0.11
    亲å¯Ĩ
    0.11
    æŀķ
    0.11
    åħ±åĪĽ
    0.10
    Activations Density 0.139%

    No Known Activations