© 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. 29788
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    çĶ¨å¿ĥ
    -0.11
    æĶ¾æīĭ
    -0.09
    anness
    -0.09
    åľ°åĿª
    -0.08
    为ä¹ĭ
    -0.08
    æĢ»é¢Ŀ
    -0.08
    æݩ饰
    -0.08
    对äºİæĪij们
    -0.08
     lect
    -0.08
    èĮĨ
    -0.08
    POSITIVE LOGITS
    éķľåŃIJ
    0.09
    esp
    0.09
     prompt
    0.09
    nst
    0.09
     Prompt
    0.09
    _prompt
    0.08
    ogle
    0.08
    prompt
    0.08
    /about
    0.08
    å¾Ģä¸ĭ
    0.08
    Activations Density 0.000%

    No Known Activations