© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26069
    Prev
    Next
    INDEX
    Explanations

    javascript disabled or browser not supported

    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
    Negative Logits
    åıĪ被
    -0.10
    å¹´é¾Ħ段
    -0.09
    å§Ĭ妹
    -0.09
    åıĪè¦ģ
    -0.09
     конÑĤÑĢол
    -0.09
    æĭ§
    -0.09
    è¦ģèĢĥèĻij
    -0.09
    ìłĪ
    -0.08
    æĺ¯å¯¹
    -0.08
    ä¸įåIJĪæł¼
    -0.08
    POSITIVE LOGITS
    ç³Ļ
    0.09
     нек
    0.09
    åĤ¬
    0.09
    ç¾İè§Ĥ
    0.09
    åĭī强
    0.09
    ç´«
    0.09
    thouse
    0.08
     pret
    0.08
    æĺ¾å¾Ĺ
    0.08
    instein
    0.08
    Activations Density 0.037%

    No Known Activations