© 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. 60731
    Prev
    Next
    INDEX
    Explanations

    study completion

    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
    åħ¥åľº
    -0.08
     pit
    -0.08
    pit
    -0.08
    åĪĽæĸ°èĥ½åĬĽ
    -0.08
    ochen
    -0.08
    漫
    -0.08
    ivan
    -0.08
    åĩºåĬ¨
    -0.08
    å±ķè§Īä¼ļ
    -0.08
    第ä¸Ģå±Ĭ
    -0.08
    POSITIVE LOGITS
    -module
    0.10
    .Modules
    0.09
    Disposition
    0.09
    çĶ»éĿ¢
    0.09
    _module
    0.09
    å©Ģ
    0.09
    åľ¨çº¿
    0.08
     completion
    0.08
    uko
    0.08
    Modules
    0.08
    Activations Density 0.058%

    No Known Activations