© 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. 6378
    Prev
    Next
    INDEX
    Explanations

    law citations

    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
    éĹ°
    -0.09
     McB
    -0.09
    æ³Ĭ
    -0.09
    æĮ£
    -0.09
    åį¿
    -0.08
    åħ¼é¡¾
    -0.08
     handed
    -0.08
    æīĪ
    -0.08
    aaS
    -0.08
    ¢åįķ
    -0.08
    POSITIVE LOGITS
    èĢĻ
    0.10
    è§Ħç«ł
    0.10
    æĿ¡
    0.10
    åĩºçİ°åľ¨
    0.09
    管çIJĨæĿ¡ä¾ĭ
    0.09
    åįģä¸ĥæĿ¡
    0.09
    ä¾Ŀæį®
    0.09
    ä»Ļå¢ĥ
    0.08
    å¥ĩ纳
    0.08
    law
    0.08
    Activations Density 0.100%

    No Known Activations