© 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. 2784
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    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
    7
    -0.12
    6
    -0.11
    3
    -0.11
    4
    -0.11
    8
    -0.10
    2
    -0.10
    5
    -0.10
    9
    -0.10
    1
    -0.10
    0
    -0.10
    POSITIVE LOGITS
    ä½Ĩä»į
    0.12
    èİ«è¿ĩäºİ
    0.12
    äºĨåIJĹ
    0.11
    çĻ½æ²Ļ
    0.11
    ä»ħ代表
    0.10
    ä¹Łæĺ¯ä¸Ģç§į
    0.10
    igli
    0.10
    éķĩåħļå§Ķ
    0.10
    ä¹ŁæŃ£æĺ¯
    0.10
    便æĺ¯
    0.10
    Activations Density 0.194%

    No Known Activations