© 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. 24121
    Prev
    Next
    INDEX
    Explanations

    cooking and eating

    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
    å¤ĸéĿ¢
    -0.10
    åĪº
    -0.10
    éĴĪ
    -0.09
    饺åŃIJ
    -0.09
    ä¸Ģçľĭ
    -0.08
    æĪij们çİ°åľ¨
    -0.08
    è¦ģåİ»
    -0.08
    æĢķ
    -0.08
    éĶIJ
    -0.08
    éĩĿ
    -0.08
    POSITIVE LOGITS
    çĤī
    0.10
    椿
    0.10
    éĩį度
    0.10
    edly
    0.09
    abin
    0.09
    å®ıä¼Ł
    0.09
    åľ¨å®¶éĩĮ
    0.09
    太ä¹ħ
    0.09
    çŁ¿çī©è´¨
    0.09
    æħ¢
    0.08
    Activations Density 0.016%

    No Known Activations