© 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. 5202
    Prev
    Next
    INDEX
    Explanations

    payment programs

    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¯Ħè®®
    -0.10
    æĬĬèĩªå·±çļĦ
    -0.10
    ä¹IJè§Ĥ
    -0.10
     Цена
    -0.09
    ÂĢÂ
    -0.09
    忧èĻij
    -0.08
    å°Ĩèĩªå·±çļĦ
    -0.08
    맥
    -0.08
    æ¡ĥ
    -0.08
     Roses
    -0.08
    POSITIVE LOGITS
    åıijæĶ¾
    0.14
    ç»ĻäºĨ
    0.12
    åħijçİ°
    0.11
    对ä»ĺ
    0.11
    å¾ħéģĩ
    0.10
    稿
    0.10
    èģĺçĶ¨
    0.10
    å½ķçĶ¨
    0.10
    ç»Ļ
    0.10
    æĶ¯ä»ĺ
    0.10
    Activations Density 0.072%

    No Known Activations