© 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. 27058
    Prev
    Next
    INDEX
    Explanations

    appointments with Jeff

    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
    çĶļèĩ³è¿ĺ
    -0.11
    æĹłçĸij
    -0.10
    éģ¿
    -0.09
    æį¢
    -0.09
    强åĬ¿
    -0.09
    并ä¸İ
    -0.09
    ä¸ĢåIJį
    -0.08
    被认为
    -0.08
    åı¯è°ĵæĺ¯
    -0.08
    à¸Ŀ
    -0.08
    POSITIVE LOGITS
    æľ¬ç½ij
    0.10
    çĺ¾
    0.10
    åľ¨æĦı
    0.10
    严ç¦ģ
    0.09
    surf
    0.09
    çĶ·å£«
    0.09
    åľ¨ç½ijä¸Ĭ
    0.09
    packed
    0.08
    åľ¨åŃ¦æł¡
    0.08
     Jeff
    0.08
    Activations Density 0.014%

    No Known Activations