© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7874
    Prev
    Next
    INDEX
    Explanations

    not at all

    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
    饮水
    -0.10
    æ¯ĭ
    -0.09
    æĽ´å¤ļ精彩
    -0.08
    çİīçŁ³
    -0.08
    ç®Ģ缴æĺ¯
    -0.08
    ç®ĢçĽ´å°±æĺ¯
    -0.08
    æĸIJ
    -0.08
    èĥ¥
    -0.08
    åĬłå¿«åıijå±ķ
    -0.08
    uable
    -0.08
    POSITIVE LOGITS
    erman
    0.11
    æĭħå¿ĥ
    0.10
    idan
    0.10
    åĽ°æī°
    0.10
     обÑĢазом
    0.09
    两家
    0.09
    enÃŃ
    0.09
    /dc
    0.09
    欢è¿İæĤ¨
    0.09
    ikel
    0.08
    Activations Density 0.003%

    No Known Activations