© 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. 29665
    Prev
    Next
    INDEX
    Explanations

    news or specific events

    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
    ä¸Ģ度
    -0.09
    ä¸įåıĺ
    -0.09
    ä¸ĢäºĽ
    -0.09
    åı¯æĥľ
    -0.09
    ãģ¯ãģĺãĤģ
    -0.09
     phÃŃa
    -0.09
    èıĬ
    -0.08
     unfortunately
    -0.08
    åĬ¿å¤´
    -0.08
    éĻIJ
    -0.08
    POSITIVE LOGITS
    å±ħçĦ¶
    0.16
    å¦ĤæѤ
    0.13
    ãģĹãģĭãĤĤ
    0.13
    ç«ŁçĦ¶
    0.13
    è¿Ļä¹Ī
    0.12
    ç«Ł
    0.12
    è¿Ļæł·ä¸Ģ个
    0.11
    æĢİä¹Īåı¯èĥ½
    0.11
    è¿Ļä¹Īå¤ļ
    0.11
    è¿Ļä¹Īä¹ħ
    0.10
    Activations Density 0.205%

    No Known Activations