© 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. 37408
    Prev
    Next
    INDEX
    Explanations

    historians and authors' names

    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
    åŃĢ
    -0.09
     è¾ĵ
    -0.09
    è§ĩ
    -0.09
    æķıæį·
    -0.09
    åĩłåįģ
    -0.08
    æĭ¥æĬ±
    -0.08
    åĮĹ约
    -0.08
    å¤ļ人
    -0.08
    ophon
    -0.08
    裹
    -0.08
    POSITIVE LOGITS
    åİĨåı²
    0.10
    ä¸Ĭä¸ĭ
    0.09
    EMU
    0.09
    æ¡¢
    0.09
    磸
    0.08
    éģĹçķĻ
    0.08
    æľ¨è´¨
    0.08
    èIJ½ä¸ĭ
    0.08
    BUFF
    0.08
    èIJ½åľ°
    0.08
    Activations Density 0.078%

    No Known Activations