© 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. 29666
    Prev
    Next
    INDEX
    Explanations

    case citations

    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
     itemprop
    -0.09
    ihan
    -0.09
    çī¡
    -0.09
    樵
    -0.09
    çģµéŃĤ
    -0.09
    çİĦ
    -0.09
    对æĪij说
    -0.08
    aura
    -0.08
    失èIJ½
    -0.08
    éķ¿è¾Ī
    -0.08
    POSITIVE LOGITS
    wagon
    0.09
    orage
    0.09
    车ç«Ļ
    0.09
    éĴ
    0.09
    çĻ¾å®¶
    0.09
    รา
    0.09
     wagon
    0.09
     Moran
    0.09
    ä¸ĩè¾Ĩ
    0.08
    Spoiler
    0.08
    Activations Density 0.057%

    No Known Activations