© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19950
    Prev
    Next
    INDEX
    Explanations

    first step explanation

    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
    纽
    -0.11
    ä¸Ģ缴å¤Ħäºİ
    -0.10
    æľĢç»Ī
    -0.10
    æĹ¢
    -0.10
    åĪļ好
    -0.10
    æŃ£å¥½
    -0.10
    ynes
    -0.09
    åıªä¼ļ
    -0.09
    æľĢçµĤ
    -0.09
    ä¸įä»ħèĥ½
    -0.09
    POSITIVE LOGITS
    åħ¶æ¬¡æĺ¯
    0.13
    çľĭä¸Ģä¸ĭ
    0.11
    谢谢
    0.10
    åħ¶æ¬¡
    0.10
    èĢĮåIJİ
    0.10
    å¼Ħ
    0.09
    ToEnd
    0.09
    æģŃåĸľ
    0.09
    å¾ĹçĽĬäºİ
    0.09
    agation
    0.08
    Activations Density 0.124%

    No Known Activations