© 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. 732
    Prev
    Next
    INDEX
    Explanations

    largest, leading, leader, only

    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
    åģļ人
    -0.09
    å¾½
    -0.09
    æľ¬æľŁ
    -0.08
    ardin
    -0.08
    çªį
    -0.08
    æ·¦
    -0.08
    çĺŁ
    -0.08
    æ³¼
    -0.08
    ç²¾çĽĬæ±Ĥç²¾
    -0.08
    åĩĨå¤ĩå·¥ä½ľ
    -0.08
    POSITIVE LOGITS
    é¢ĨåħĪçļĦ
    0.11
    æĿĥå¨ģ
    0.11
    ä¸ĵ注
    0.11
    CLICK
    0.10
    è§Ħ模æľĢ大
    0.10
     orient
    0.09
    æľįåĬ¡å¹³åı°
    0.09
    æĥħ趣
    0.09
    å¹³åı°ä¸Ĭ
    0.08
     comprehensive
    0.08
    Activations Density 0.220%

    No Known Activations