© 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. 60557
    Prev
    Next
    INDEX
    Explanations

    primarily or predominantly

    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
    è¿Ļä¹Łæĺ¯
    -0.12
    éĻ¤æѤ
    -0.09
    å¤Ħå¤Ħ
    -0.09
    éļĨéĩį
    -0.09
    为åķ¥
    -0.09
    ervo
    -0.09
    ç¼ķ
    -0.08
     вÑģÑı
    -0.08
    ammer
    -0.08
    å®ĥæĺ¯
    -0.08
    POSITIVE LOGITS
     Skinner
    0.10
    acles
    0.10
    è¿ĩéĶĻ
    0.09
    ãģ©ãģĵãĤį
    0.09
    acle
    0.09
    lod
    0.08
    ä¸ĭåİ»
    0.08
    马æĭī
    0.08
    ä½ĵçİ°åľ¨
    0.08
    äºĭåħĪ
    0.08
    Activations Density 0.045%

    No Known Activations