© 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. 12220
    Prev
    Next
    INDEX
    Explanations

    less than

    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¸įä¸ĭ
    -0.12
    å·®ä¸įå¤ļ
    -0.10
    è¥Ħ
    -0.10
    ä¸įéĶĻ
    -0.10
    ä¸į妨
    -0.10
    大æ¦Ĥæĺ¯
    -0.10
     zwar
    -0.10
    æģ°
    -0.09
    主ä¹īæĢĿæĥ³
    -0.09
    MEA
    -0.09
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.12
     (\<
    0.12
    åħ¨éĿ¢èIJ½å®ŀ
    0.11
     (<
    0.10
    ä½Ķ
    0.09
    çİĭèĢħ
    0.09
    çļĦæĥħåĨµä¸ĭ
    0.09
    çĺ¾
    0.09
    åĽŀäºĭ
    0.09
    çīĩåĪ»
    0.08
    Activations Density 0.054%

    No Known Activations