© 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. 24209
    Prev
    Next
    INDEX
    Explanations

    best known

    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
    åįĥåı¤
    -0.10
     bat
    -0.09
    è¾ķ
    -0.09
    éĺ¶
    -0.09
    tti
    -0.09
    bat
    -0.09
    èĢ¸
    -0.08
    бÑĥ
    -0.08
    åįĥéĩĮ
    -0.08
    æ¯ı次éĥ½
    -0.08
    POSITIVE LOGITS
    路桥
    0.10
     оÑĦоÑĢм
    0.09
    æ¦Ĥæĭ¬
    0.09
    说æĺ¯
    0.09
    ä»Ģä¹Īäºĭ
    0.09
    说ä»Ģä¹Ī
    0.08
    iners
    0.08
    解读
    0.08
    æııè¿°
    0.08
    ritos
    0.08
    Activations Density 0.070%

    No Known Activations