© 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. 63976
    Prev
    Next
    INDEX
    Explanations

    property of

    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
    äºĨèĩªå·±çļĦ
    -0.09
    äºĨä»ĸçļĦ
    -0.09
    çĬ¯
    -0.09
    æ²īéĩį
    -0.09
    å´ĩé«ĺ
    -0.09
    åĸĨ
    -0.08
    为æ°ij
    -0.08
    /rfc
    -0.08
    è¨Ń
    -0.08
    ä»ĸ们æĺ¯
    -0.08
    POSITIVE LOGITS
    主管éĥ¨éŨ
    0.10
    çij
    0.09
    çĶ¨æĪ·æıIJä¾Ľ
    0.09
    kees
    0.09
    绣çŃ¹
    0.09
    殡
    0.09
    ASH
    0.08
     lẫn
    0.08
    irst
    0.08
    ACK
    0.08
    Activations Density 0.010%

    No Known Activations