© 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. 24155
    Prev
    Next
    INDEX
    Explanations

    before followed by a transition

    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
    رش
    -0.11
    å°±è¿Ļä¹Ī
    -0.11
    å°±è¿Ļæł·
    -0.10
    guard
    -0.09
    -Ray
    -0.09
     cứ
    -0.09
    宾客
    -0.08
    æĹ¢æľī
    -0.08
    ILE
    -0.08
    mtx
    -0.08
    POSITIVE LOGITS
    åıĹåĪ°
    0.09
    æłĩåĩĨåĮĸ
    0.09
    ENN
    0.08
    æĥĬåı¹
    0.08
    åĬª
    0.08
    -toggle
    0.08
    зи
    0.08
    å¸ĤæķĻèĤ²å±Ģ
    0.08
    åľ¨åħ¨åĽ½
    0.08
    èĭĩ
    0.08
    Activations Density 0.021%

    No Known Activations