© 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. 47482
    Prev
    Next
    INDEX
    Explanations

    as an argument

    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
    ERY
    -0.10
    å°±æĺ¯åĽłä¸º
    -0.09
    9
    -0.09
    å°±è¿Ļä¹Ī
    -0.09
    æijĩäºĨæijĩ头
    -0.08
    æijĩ头
    -0.08
    5
    -0.08
     Cardinal
    -0.08
    4
    -0.08
    åħĪ天
    -0.08
    POSITIVE LOGITS
    åıĤæķ°
    0.10
    æŃī
    0.09
    ä¸Ģç»Ħ
    0.09
    è¢ĭåŃIJ
    0.09
     either
    0.09
     коÑĤоÑĢ
    0.09
     dazu
    0.09
    -Sah
    0.09
    ubby
    0.09
    è¦ģä¹Ī
    0.09
    Activations Density 0.691%

    No Known Activations