© 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. 16631
    Prev
    Next
    INDEX
    Explanations

    sharing personal discoveries and experiences

    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
    tgt
    -0.10
    æĴŃç§į
    -0.10
    SAMPLE
    -0.09
    楼主
    -0.09
     Reviewed
    -0.09
    æľīæľº
    -0.09
    åİĺ
    -0.09
     ÙĬÙĤÙĪÙĦ
    -0.09
    éĺħ读åħ¨æĸĩ
    -0.09
    å¾Ģå¤ĸ
    -0.09
    POSITIVE LOGITS
    æĢĿèĢĥ
    0.09
    ÑĪÑĥ
    0.09
    jur
    0.08
    éŀį
    0.08
    æµ·ä¸Ĭ
    0.08
     Baron
    0.08
    æĶ¶åĪ°
    0.08
    unsch
    0.08
    è¿ĻäºĽå¹´
    0.08
    æIJ¬
    0.08
    Activations Density 0.169%

    No Known Activations