© 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. 7012
    Prev
    Next
    INDEX
    Explanations

    then followed by 'you' or action

    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
    è¿ĺè®°å¾Ĺ
    -0.11
    ä¸įä¸ĭ
    -0.10
    æľ¬ç½ijç«Ļ
    -0.10
    å¿ĻçĿĢ
    -0.09
    ä»Ģä¹ĪåİŁåĽł
    -0.09
    è¿Ļæĺ¯åĽłä¸º
    -0.09
    Invoker
    -0.09
    æĭĽçīĮ
    -0.09
    åľ³
    -0.09
    å°ĨåĨĽ
    -0.09
    POSITIVE LOGITS
    åIJİæĿ¥
    0.10
    Ùħص
    0.10
    later
    0.10
     later
    0.09
    åĨįåĬłä¸Ĭ
    0.09
    eten
    0.09
    诸
    0.09
    å¾Įä¾Ĩ
    0.09
    anke
    0.09
    篦
    0.08
    Activations Density 0.044%

    No Known Activations